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

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

Neuron 966 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3251. Min Act: -0.0001

Data Index: 1511348 (Python Code)

Max Activating Token Index: 432

Text #1

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2857. Min Act: -0.0001

Data Index: 535003 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2878. Min Act: -0.0001

Data Index: 1317082 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2609. Min Act: -0.0001

Data Index: 339725 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2766. Min Act: -0.0001

Data Index: 574701 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2412. Min Act: -0.0001

Data Index: 611550 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2570. Min Act: -0.0001

Data Index: 247749 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2409. Min Act: -0.0001

Data Index: 1227805 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1025880 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2363. Min Act: -0.0001

Data Index: 570872 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2392. Min Act: -0.0001

Data Index: 552343 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1323450 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2191. Min Act: -0.0001

Data Index: 308583 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2210. Min Act: -0.0001

Data Index: 515663 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2072. Min Act: -0.0001

Data Index: 554495 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2196. Min Act: -0.0001

Data Index: 974066 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2154. Min Act: -0.0001

Data Index: 863421 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2150. Min Act: -0.0001

Data Index: 283874 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2136. Min Act: -0.0001

Data Index: 1297067 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2046. Min Act: -0.0001

Data Index: 183774 (C4 (Web Text))

Max Activating Token Index: 570