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

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

Neuron 2226 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2328. Min Range: -3.2328

Max Act: 3.2328. Min Act: -0.0000

Data Index: 1084441 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.1772. Min Act: -0.0000

Data Index: 1033916 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.9485. Min Act: -0.0000

Data Index: 176072 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.8166. Min Act: -0.0000

Data Index: 523540 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.8906. Min Act: -0.0000

Data Index: 115937 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1074385 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.7294. Min Act: -0.0000

Data Index: 504149 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.8266. Min Act: -0.0000

Data Index: 893876 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.8086. Min Act: -0.0000

Data Index: 952469 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.8207. Min Act: -0.0000

Data Index: 285591 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.6994. Min Act: -0.0000

Data Index: 1304301 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.8293. Min Act: -0.0000

Data Index: 312616 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.7100. Min Act: -0.0000

Data Index: 912157 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.6762. Min Act: -0.0000

Data Index: 1192170 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.6518. Min Act: -0.0000

Data Index: 194963 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.6015. Min Act: -0.0000

Data Index: 1259268 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.6159. Min Act: -0.0000

Data Index: 827583 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.5868. Min Act: -0.0000

Data Index: 1159534 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.5228. Min Act: -0.0000

Data Index: 1104665 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 3.2328. Min Range: -3.2328

Max Act: 1.5104. Min Act: -0.0000

Data Index: 1353794 (C4 (Web Text))

Max Activating Token Index: 492