Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2565 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2970. Min Act: -0.0000

Data Index: 309638 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2693. Min Act: -0.0000

Data Index: 204686 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1010856 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2516. Min Act: -0.0000

Data Index: 847625 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2513. Min Act: -0.0000

Data Index: 961187 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1230647 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2353. Min Act: -0.0000

Data Index: 575759 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2531. Min Act: -0.0000

Data Index: 28075 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1207563 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1151358 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2315. Min Act: -0.0000

Data Index: 592383 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2290. Min Act: -0.0000

Data Index: 926358 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1097608 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2127. Min Act: -0.0000

Data Index: 320361 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2072. Min Act: -0.0000

Data Index: 276983 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2203. Min Act: -0.0000

Data Index: 919 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2057. Min Act: -0.0000

Data Index: 422028 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2137. Min Act: -0.0000

Data Index: 200315 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2108. Min Act: -0.0000

Data Index: 975446 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2115. Min Act: -0.0000

Data Index: 281684 (C4 (Web Text))

Max Activating Token Index: 219