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

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

Neuron 5296 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1204910 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3069. Min Act: -0.0000

Data Index: 87406 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2579. Min Act: -0.0000

Data Index: 12079 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1088816 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2707. Min Act: -0.0000

Data Index: 455195 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2532. Min Act: -0.0000

Data Index: 50432 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2260. Min Act: -0.0000

Data Index: 116689 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2445. Min Act: -0.0000

Data Index: 817296 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2292. Min Act: -0.0000

Data Index: 599879 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1155505 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2231. Min Act: -0.0000

Data Index: 525831 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2197. Min Act: -0.0000

Data Index: 486683 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2186. Min Act: -0.0000

Data Index: 845858 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1503052 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2370. Min Act: -0.0000

Data Index: 576925 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2409. Min Act: -0.0000

Data Index: 410250 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2209. Min Act: -0.0000

Data Index: 138870 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1110424 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1276448 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2071. Min Act: -0.0000

Data Index: 969494 (C4 (Web Text))

Max Activating Token Index: 747