< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 72 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1912273 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1872820 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1231. Min Act: -0.0001

Data Index: 220038 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1222. Min Act: -0.0001

Data Index: 698439 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1233. Min Act: -0.0001

Data Index: 393598 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1476258 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1890506 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1254. Min Act: -0.0001

Data Index: 242542 (The Pile)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1191. Min Act: -0.0001

Data Index: 818569 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1275. Min Act: -0.0001

Data Index: 404137 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1309. Min Act: -0.0001

Data Index: 663503 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1218. Min Act: -0.0001

Data Index: 814367 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1965014 (The Pile)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1261. Min Act: -0.0001

Data Index: 213043 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1258. Min Act: -0.0001

Data Index: 308785 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1983628 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1123. Min Act: -0.0001

Data Index: 3650 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1641864 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1202. Min Act: -0.0001

Data Index: 683064 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1497562 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #19