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

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

Neuron 201 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: 0.1234. Min Range: -0.1234

Max Act: 0.1234. Min Act: -0.0002

Data Index: 416404 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1178. Min Act: -0.0002

Data Index: 857511 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1090. Min Act: -0.0002

Data Index: 629582 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1332364 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1017. Min Act: -0.0002

Data Index: 752021 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1177. Min Act: -0.0002

Data Index: 1214879 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1334683 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1067. Min Act: -0.0002

Data Index: 1251801 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1050433 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0970. Min Act: -0.0002

Data Index: 112278 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0989. Min Act: -0.0002

Data Index: 855265 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0992. Min Act: -0.0002

Data Index: 525053 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1060. Min Act: -0.0002

Data Index: 545066 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0985. Min Act: -0.0002

Data Index: 45180 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0945. Min Act: -0.0002

Data Index: 397643 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0964. Min Act: -0.0002

Data Index: 339854 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1165. Min Act: -0.0002

Data Index: 780780 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0955. Min Act: -0.0002

Data Index: 424166 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0967. Min Act: -0.0002

Data Index: 748015 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0894. Min Act: -0.0002

Data Index: 966466 (C4 (Web Text))

Max Activating Token Index: 688