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

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

Neuron 237 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4542. Min Act: -0.0001

Data Index: 171421 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4241. Min Act: -0.0000

Data Index: 284398 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3848. Min Act: -0.0000

Data Index: 452160 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3924. Min Act: -0.0000

Data Index: 10050 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3612. Min Act: -0.0000

Data Index: 581739 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3855. Min Act: -0.0001

Data Index: 1145054 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1256399 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3280. Min Act: -0.0000

Data Index: 503940 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3380. Min Act: -0.0001

Data Index: 1243523 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3271. Min Act: -0.0000

Data Index: 305654 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1179470 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3218. Min Act: -0.0000

Data Index: 305549 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3222. Min Act: -0.0000

Data Index: 42805 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3170. Min Act: -0.0000

Data Index: 783912 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1095627 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3461. Min Act: -0.0001

Data Index: 202017 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3179. Min Act: -0.0000

Data Index: 975711 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1019248 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2945. Min Act: -0.0001

Data Index: 1221217 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3154. Min Act: -0.0001

Data Index: 1019065 (C4 (Web Text))

Max Activating Token Index: 438