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

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

Neuron 4707 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6194. Min Act: -0.0000

Data Index: 862205 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6574. Min Act: -0.0000

Data Index: 623867 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5923. Min Act: -0.0000

Data Index: 331175 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6351. Min Act: -0.0000

Data Index: 861032 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6015. Min Act: -0.0000

Data Index: 307629 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6381. Min Act: -0.0000

Data Index: 570761 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1105272 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5876. Min Act: -0.0000

Data Index: 460632 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1068604 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1241571 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5498. Min Act: -0.0000

Data Index: 456844 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5476. Min Act: -0.0000

Data Index: 578986 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5450. Min Act: -0.0000

Data Index: 339827 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5459. Min Act: -0.0000

Data Index: 871372 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5213. Min Act: -0.0000

Data Index: 869032 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5369. Min Act: -0.0000

Data Index: 926680 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1250433 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5272. Min Act: -0.0000

Data Index: 987614 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5253. Min Act: -0.0000

Data Index: 60304 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5203. Min Act: -0.0000

Data Index: 958121 (C4 (Web Text))

Max Activating Token Index: 851