Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2645 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.4308. Min Act: -0.0001

Data Index: 1016488 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3609. Min Act: -0.0001

Data Index: 1299235 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3315. Min Act: -0.0001

Data Index: 332788 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3187. Min Act: -0.0001

Data Index: 904087 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3264. Min Act: -0.0001

Data Index: 286138 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3253. Min Act: -0.0001

Data Index: 172370 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3228. Min Act: -0.0001

Data Index: 860594 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3145. Min Act: -0.0001

Data Index: 873810 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3088. Min Act: -0.0001

Data Index: 773380 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1127438 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3022. Min Act: -0.0000

Data Index: 100800 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2901. Min Act: -0.0001

Data Index: 899786 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2754. Min Act: -0.0000

Data Index: 143225 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2737. Min Act: -0.0001

Data Index: 574594 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1174432 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2786. Min Act: -0.0001

Data Index: 876508 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2852. Min Act: -0.0001

Data Index: 271845 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2874. Min Act: -0.0001

Data Index: 1336764 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2868. Min Act: -0.0001

Data Index: 700031 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2737. Min Act: -0.0000

Data Index: 444048 (C4 (Web Text))

Max Activating Token Index: 537