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

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

Neuron 643 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.6392. Min Act: -0.0001

Data Index: 135814 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5988. Min Act: -0.0001

Data Index: 539691 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.6348. Min Act: -0.0001

Data Index: 544658 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5629. Min Act: -0.0001

Data Index: 41098 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5872. Min Act: -0.0001

Data Index: 545015 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5524. Min Act: -0.0001

Data Index: 1225212 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5636. Min Act: -0.0001

Data Index: 541494 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5586. Min Act: -0.0001

Data Index: 1076831 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5863. Min Act: -0.0001

Data Index: 666448 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5319. Min Act: -0.0001

Data Index: 159955 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5245. Min Act: -0.0001

Data Index: 472862 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5304. Min Act: -0.0001

Data Index: 936198 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5266. Min Act: -0.0001

Data Index: 973649 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5078. Min Act: -0.0001

Data Index: 1153218 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5192. Min Act: -0.0001

Data Index: 1242502 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5023. Min Act: -0.0001

Data Index: 50285 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5123. Min Act: -0.0001

Data Index: 1061187 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5113. Min Act: -0.0001

Data Index: 1078875 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5303. Min Act: -0.0001

Data Index: 221717 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4941. Min Act: -0.0001

Data Index: 765377 (C4 (Web Text))

Max Activating Token Index: 532