Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 862 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3948. Min Act: -0.0003

Data Index: 1231771 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.4031. Min Act: -0.0003

Data Index: 1136905 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3613. Min Act: -0.0003

Data Index: 992889 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2835. Min Act: -0.0003

Data Index: 64021 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3457. Min Act: -0.0003

Data Index: 701093 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3536. Min Act: -0.0003

Data Index: 1302794 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3001. Min Act: -0.0003

Data Index: 1345738 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3318. Min Act: -0.0003

Data Index: 166799 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3165. Min Act: -0.0003

Data Index: 831697 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3660. Min Act: -0.0003

Data Index: 233245 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3306. Min Act: -0.0003

Data Index: 759311 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3573. Min Act: -0.0003

Data Index: 484226 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3098. Min Act: -0.0003

Data Index: 641289 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3380. Min Act: -0.0003

Data Index: 358433 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3590. Min Act: -0.0003

Data Index: 992554 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3341. Min Act: -0.0003

Data Index: 305213 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3392. Min Act: -0.0003

Data Index: 646653 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2897. Min Act: -0.0003

Data Index: 166104 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3081. Min Act: -0.0003

Data Index: 1140304 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2972. Min Act: -0.0003

Data Index: 920275 (C4 (Web Text))

Max Activating Token Index: 33