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

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

Neuron 4259 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: 0.6440. Min Range: -0.6440

Max Act: 0.6440. Min Act: -0.0000

Data Index: 458983 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.6369. Min Act: -0.0000

Data Index: 88594 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.6138. Min Act: -0.0000

Data Index: 377495 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5805. Min Act: -0.0000

Data Index: 309353 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5622. Min Act: -0.0000

Data Index: 893053 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5658. Min Act: -0.0000

Data Index: 449416 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5352. Min Act: -0.0000

Data Index: 602872 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5226. Min Act: -0.0000

Data Index: 40458 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1295746 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5091. Min Act: -0.0000

Data Index: 927810 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5157. Min Act: -0.0000

Data Index: 140715 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1338164 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4966. Min Act: -0.0000

Data Index: 108586 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5073. Min Act: -0.0000

Data Index: 356894 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1116885 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5000. Min Act: 0.0000

Data Index: 1150220 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4941. Min Act: -0.0000

Data Index: 293073 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4911. Min Act: -0.0000

Data Index: 485000 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4897. Min Act: -0.0000

Data Index: 331932 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4833. Min Act: 0.0000

Data Index: 193065 (C4 (Web Text))

Max Activating Token Index: 804