< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 20 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1466. Min Act: -0.0004

Data Index: 1878050 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1346. Min Act: -0.0004

Data Index: 1015986 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1307. Min Act: -0.0004

Data Index: 319583 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1288. Min Act: -0.0004

Data Index: 1036699 (The Pile)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1275. Min Act: -0.0004

Data Index: 634343 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1268. Min Act: -0.0004

Data Index: 65652 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1309. Min Act: -0.0004

Data Index: 902536 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1343. Min Act: -0.0004

Data Index: 676587 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1191. Min Act: -0.0004

Data Index: 1482416 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1264. Min Act: -0.0004

Data Index: 330777 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1325. Min Act: -0.0004

Data Index: 745866 (The Pile)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1184. Min Act: -0.0004

Data Index: 973760 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1203. Min Act: -0.0004

Data Index: 1260970 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1205. Min Act: -0.0004

Data Index: 808202 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1249. Min Act: -0.0004

Data Index: 682709 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1224. Min Act: -0.0004

Data Index: 923665 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1235. Min Act: -0.0004

Data Index: 768901 (The Pile)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1234. Min Act: -0.0004

Data Index: 432407 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1233. Min Act: -0.0004

Data Index: 1810899 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1208. Min Act: -0.0004

Data Index: 529580 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #19