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

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

Neuron 2929 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: 1.7955. Min Range: -1.7955

Max Act: 1.7955. Min Act: -0.0002

Data Index: 274873 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.7792. Min Act: -0.0002

Data Index: 1049129 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1605. Min Act: -0.0002

Data Index: 254408 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.6390. Min Act: -0.0002

Data Index: 693207 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1798. Min Act: -0.0002

Data Index: 498842 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1420. Min Act: -0.0002

Data Index: 1011928 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1135. Min Act: -0.0002

Data Index: 344602 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.2223. Min Act: -0.0002

Data Index: 40787 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.7955. Min Range: -1.7955

Max Act: 0.9913. Min Act: -0.0002

Data Index: 928014 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1559. Min Act: -0.0002

Data Index: 1212758 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1896. Min Act: -0.0002

Data Index: 727499 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.0597. Min Act: -0.0002

Data Index: 3111 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1082. Min Act: -0.0002

Data Index: 295351 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.0256. Min Act: -0.0002

Data Index: 211857 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.2331. Min Act: -0.0002

Data Index: 655803 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.0484. Min Act: -0.0002

Data Index: 672796 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.2262. Min Act: -0.0002

Data Index: 848439 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.7955. Min Range: -1.7955

Max Act: 0.9435. Min Act: -0.0002

Data Index: 1026085 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.2362. Min Act: -0.0002

Data Index: 657376 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 1.7955. Min Range: -1.7955

Max Act: 1.1297. Min Act: -0.0002

Data Index: 1225635 (C4 (Web Text))

Max Activating Token Index: 773