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

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

Neuron 4584 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: 0.4061. Min Range: -0.4061

Max Act: 0.4061. Min Act: -0.0000

Data Index: 763700 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1339959 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3637. Min Act: 0.0001

Data Index: 800586 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1211519 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3466. Min Act: -0.0000

Data Index: 966106 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3552. Min Act: -0.0000

Data Index: 544647 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3534. Min Act: -0.0000

Data Index: 875768 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3632. Min Act: -0.0000

Data Index: 30896 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1339068 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3542. Min Act: -0.0000

Data Index: 612815 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3394. Min Act: -0.0000

Data Index: 586896 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3347. Min Act: 0.0001

Data Index: 1021939 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3321. Min Act: -0.0000

Data Index: 325145 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1096309 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1090597 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3312. Min Act: -0.0000

Data Index: 961589 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3308. Min Act: -0.0000

Data Index: 616726 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1315046 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3158. Min Act: -0.0000

Data Index: 468623 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3201. Min Act: -0.0000

Data Index: 778680 (C4 (Web Text))

Max Activating Token Index: 817