Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3326 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3208. Min Range: -2.3208

Max Act: 2.3208. Min Act: -0.0000

Data Index: 681842 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 2.3208. Min Range: -2.3208

Max Act: 2.1220. Min Act: -0.0000

Data Index: 1101565 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.9678. Min Act: -0.0000

Data Index: 1315819 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.8791. Min Act: -0.0000

Data Index: 58259 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.7855. Min Act: -0.0000

Data Index: 769054 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.8323. Min Act: -0.0000

Data Index: 953488 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.8230. Min Act: -0.0000

Data Index: 852469 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.6710. Min Act: -0.0000

Data Index: 874200 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.6328. Min Act: -0.0000

Data Index: 779421 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.6287. Min Act: -0.0000

Data Index: 356460 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.2834. Min Act: -0.0000

Data Index: 83282 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.2464. Min Act: -0.0000

Data Index: 163100 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.1550. Min Act: -0.0000

Data Index: 826400 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.0784. Min Act: -0.0000

Data Index: 94064 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.3208. Min Range: -2.3208

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1264947 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1016634 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 2.3208. Min Range: -2.3208

Max Act: 1.0150. Min Act: -0.0000

Data Index: 1022427 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 2.3208. Min Range: -2.3208

Max Act: 0.9713. Min Act: -0.0000

Data Index: 683491 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 2.3208. Min Range: -2.3208

Max Act: 0.9147. Min Act: -0.0000

Data Index: 28562 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 2.3208. Min Range: -2.3208

Max Act: 0.9587. Min Act: -0.0000

Data Index: 712656 (C4 (Web Text))

Max Activating Token Index: 655