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

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

Neuron 3523 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.6879. Min Act: -0.0002

Data Index: 1182008 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.6236. Min Act: -0.0002

Data Index: 887560 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.4992. Min Act: -0.0002

Data Index: 854636 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.4020. Min Act: -0.0002

Data Index: 540026 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.4106. Min Act: -0.0002

Data Index: 476900 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.4315. Min Act: -0.0002

Data Index: 750496 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.3911. Min Act: -0.0002

Data Index: 307970 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.2774. Min Act: -0.0002

Data Index: 691408 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.3289. Min Act: -0.0002

Data Index: 818287 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.3905. Min Act: -0.0002

Data Index: 1163700 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.2781. Min Act: -0.0002

Data Index: 716035 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.2990. Min Act: -0.0002

Data Index: 584403 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.3068. Min Act: -0.0002

Data Index: 822925 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.3272. Min Act: -0.0002

Data Index: 1169836 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.4002. Min Act: -0.0002

Data Index: 422574 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.3329. Min Act: -0.0002

Data Index: 187890 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.2840. Min Act: -0.0002

Data Index: 480411 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.2617. Min Act: -0.0002

Data Index: 421527 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.2878. Min Act: -0.0002

Data Index: 406748 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 1.6879. Min Range: -1.6879

Max Act: 1.2876. Min Act: -0.0002

Data Index: 705198 (C4 (Web Text))

Max Activating Token Index: 532