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

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

Neuron 3408 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.3041. Min Act: -0.0000

Data Index: 522153 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.3229. Min Act: -0.0000

Data Index: 148296 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2812. Min Act: -0.0000

Data Index: 104722 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.3085. Min Act: -0.0000

Data Index: 647435 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2882. Min Act: -0.0000

Data Index: 464188 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2588. Min Act: -0.0000

Data Index: 896119 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2627. Min Act: -0.0000

Data Index: 454894 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1113072 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1310052 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2205. Min Act: -0.0000

Data Index: 871531 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2426. Min Act: -0.0000

Data Index: 449788 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2185. Min Act: -0.0000

Data Index: 11966 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2296. Min Act: -0.0000

Data Index: 898115 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1142458 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2196. Min Act: -0.0000

Data Index: 85526 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2253. Min Act: -0.0000

Data Index: 841063 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2050. Min Act: -0.0000

Data Index: 962411 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1254396 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.1858. Min Act: -0.0000

Data Index: 301866 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.3229. Min Range: -0.3229

Max Act: 0.2189. Min Act: -0.0000

Data Index: 906481 (C4 (Web Text))

Max Activating Token Index: 218