Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1434 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1745651 (The Pile)

Max Activating Token Index: 925

Text #1

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1334646 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.1032. Min Act: -0.0000

Data Index: 447183 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0814. Min Act: -0.0000

Data Index: 86883 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0620. Min Act: -0.0000

Data Index: 532425 (The Pile)

Max Activating Token Index: 503

Text #5

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1466771 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1274627 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1109247 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0430. Min Act: -0.0000

Data Index: 636090 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.9842. Min Act: -0.0000

Data Index: 545384 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0249. Min Act: -0.0000

Data Index: 406281 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.9743. Min Act: -0.0000

Data Index: 644133 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0096. Min Act: -0.0000

Data Index: 919265 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1857168 (The Pile)

Max Activating Token Index: 522

Text #14

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.9774. Min Act: -0.0000

Data Index: 740703 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 1.2142. Min Range: -1.2142

Max Act: 1.0010. Min Act: -0.0000

Data Index: 457285 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1428352 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.9239. Min Act: -0.0000

Data Index: 669551 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1693853 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 1.2142. Min Range: -1.2142

Max Act: 0.9223. Min Act: -0.0000

Data Index: 36770 (The Pile)

Max Activating Token Index: 961