Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3465 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.4411. Min Act: -0.0001

Data Index: 487338 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3561. Min Act: -0.0000

Data Index: 476013 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3524. Min Act: -0.0000

Data Index: 988205 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3297. Min Act: -0.0000

Data Index: 674690 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3186. Min Act: -0.0000

Data Index: 4790 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3225. Min Act: -0.0000

Data Index: 551295 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3131. Min Act: -0.0000

Data Index: 998155 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3206. Min Act: 0.0000

Data Index: 989276 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3183. Min Act: -0.0000

Data Index: 841275 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3260. Min Act: -0.0001

Data Index: 521136 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3213. Min Act: -0.0000

Data Index: 257223 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.2925. Min Act: -0.0001

Data Index: 10983 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.3004. Min Act: -0.0000

Data Index: 375452 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1169993 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.2728. Min Act: -0.0001

Data Index: 755612 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.2935. Min Act: -0.0001

Data Index: 976121 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.2835. Min Act: -0.0001

Data Index: 819155 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1131051 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.2931. Min Act: 0.0001

Data Index: 317951 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.4411. Min Range: -0.4411

Max Act: 0.2787. Min Act: -0.0001

Data Index: 627100 (C4 (Web Text))

Max Activating Token Index: 461