< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 23 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.7119. Min Act: -0.1697

Data Index: 4523476 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.5241. Min Act: -0.1700

Data Index: 8537038 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.9309. Min Act: -0.1700

Data Index: 3325849 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.4927. Min Act: -0.1700

Data Index: 8511294 (The Pile)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3987. Min Act: -0.1699

Data Index: 2548897 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.8527. Min Act: -0.1700

Data Index: 2866307 (The Pile)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.5554. Min Act: -0.1700

Data Index: 3089030 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.6650. Min Act: -0.1699

Data Index: 2329841 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.6337. Min Act: -0.1700

Data Index: 8641873 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3359. Min Act: -0.1699

Data Index: 959835 (The Pile)

Max Activating Token Index: 816

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.6024. Min Act: -0.1700

Data Index: 2428099 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.6024. Min Act: -0.1699

Data Index: 1438323 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.2417. Min Act: -0.1699

Data Index: 9679828 (The Pile)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.5084. Min Act: -0.1699

Data Index: 884054 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.2888. Min Act: -0.1683

Data Index: 5538645 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.2888. Min Act: -0.1696

Data Index: 4197719 (The Pile)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3516. Min Act: -0.1700

Data Index: 9320423 (The Pile)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.4771. Min Act: -0.1700

Data Index: 837203 (The Pile)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.4771. Min Act: -0.1700

Data Index: 761250 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3359. Min Act: -0.1700

Data Index: 10190793 (The Pile)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #19