Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3108 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7125. Min Range: -2.7125

Max Act: 2.7125. Min Act: -0.0000

Data Index: 802338 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 2.7125. Min Range: -2.7125

Max Act: 2.4164. Min Act: -0.0000

Data Index: 547036 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 2.7125. Min Range: -2.7125

Max Act: 2.3025. Min Act: -0.0000

Data Index: 25246 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.9779. Min Act: -0.0000

Data Index: 1197667 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.8383. Min Act: -0.0000

Data Index: 587134 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.8168. Min Act: -0.0000

Data Index: 1043046 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.7954. Min Act: -0.0000

Data Index: 1353920 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.7097. Min Act: -0.0000

Data Index: 1014383 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.7056. Min Act: -0.0000

Data Index: 198310 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.6187. Min Act: -0.0000

Data Index: 163698 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.6127. Min Act: -0.0000

Data Index: 264550 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.5764. Min Act: -0.0000

Data Index: 12631 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.4962. Min Act: -0.0000

Data Index: 626638 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.5582. Min Act: -0.0000

Data Index: 870659 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.4555. Min Act: -0.0000

Data Index: 760634 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.4135. Min Act: -0.0000

Data Index: 1173568 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1158703 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1099747 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.3897. Min Act: -0.0000

Data Index: 700343 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 2.7125. Min Range: -2.7125

Max Act: 1.3672. Min Act: -0.0000

Data Index: 302649 (C4 (Web Text))

Max Activating Token Index: 98