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

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

Neuron 3555 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: 0.3444. Min Range: -0.3444

Max Act: 0.3416. Min Act: -0.0000

Data Index: 434762 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3444. Min Act: -0.0000

Data Index: 875508 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3312. Min Act: -0.0000

Data Index: 154934 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1306466 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1161110 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3268. Min Act: -0.0000

Data Index: 895450 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3363. Min Act: -0.0000

Data Index: 227207 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1314704 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3246. Min Act: -0.0000

Data Index: 311596 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3274. Min Act: -0.0000

Data Index: 287980 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3154. Min Act: -0.0000

Data Index: 548786 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3228. Min Act: -0.0000

Data Index: 937708 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3068. Min Act: -0.0000

Data Index: 443576 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3070. Min Act: -0.0000

Data Index: 998909 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1238096 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1340242 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2911. Min Act: -0.0000

Data Index: 465076 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2938. Min Act: -0.0000

Data Index: 166285 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2927. Min Act: -0.0000

Data Index: 989441 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.3444. Min Range: -0.3444

Max Act: 0.2935. Min Act: -0.0000

Data Index: 40537 (C4 (Web Text))

Max Activating Token Index: 250