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

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

Neuron 1235 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.3174. Min Act: -0.0000

Data Index: 905055 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2971. Min Act: -0.0000

Data Index: 683738 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2957. Min Act: -0.0000

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2911. Min Act: -0.0000

Data Index: 284613 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2312. Min Act: -0.0000

Data Index: 649632 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2602. Min Act: -0.0000

Data Index: 784193 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2776. Min Act: -0.0000

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2646. Min Act: -0.0000

Data Index: 236918 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1179955 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2228. Min Act: -0.0000

Data Index: 19657 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2183. Min Act: -0.0000

Data Index: 739487 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2537. Min Act: -0.0000

Data Index: 73677 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2237. Min Act: -0.0000

Data Index: 346173 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2223. Min Act: -0.0000

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1267861 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2285. Min Act: -0.0000

Data Index: 32087 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2244. Min Act: -0.0000

Data Index: 713480 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.2215. Min Act: -0.0000

Data Index: 657231 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.1931. Min Act: -0.0000

Data Index: 455124 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.3174. Min Range: -0.3174

Max Act: 0.1905. Min Act: -0.0000

Data Index: 911335 (C4 (Web Text))

Max Activating Token Index: 292