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

Dataset: The Pile

Neuron 2597 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: 1.1552. Min Range: -1.1552

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1176450 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1477499 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1776314 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1908523 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8841. Min Act: -0.0000

Data Index: 868885 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1537986 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1667553 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1028303 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8237. Min Act: -0.0000

Data Index: 806116 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1938656 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7470. Min Act: -0.0000

Data Index: 1592346 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8376. Min Act: -0.0000

Data Index: 153110 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1531913 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7312. Min Act: -0.0000

Data Index: 508716 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8124. Min Act: -0.0000

Data Index: 958429 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1977696 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7797. Min Act: -0.0000

Data Index: 728472 (The Pile)

Max Activating Token Index: 260

Text #17

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1935116 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7511. Min Act: -0.0000

Data Index: 43800 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.6811. Min Act: -0.0000

Data Index: 849198 (The Pile)

Max Activating Token Index: 820