Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 486 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.3170. Min Act: -0.0001

Data Index: 336223 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2564. Min Act: -0.0001

Data Index: 150178 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2753. Min Act: -0.0001

Data Index: 12411 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1094571 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2556. Min Act: -0.0001

Data Index: 711575 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2371. Min Act: -0.0001

Data Index: 18952 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2453. Min Act: -0.0000

Data Index: 374115 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2173. Min Act: -0.0001

Data Index: 1279821 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2201. Min Act: -0.0001

Data Index: 1150166 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2262. Min Act: -0.0001

Data Index: 550018 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2404. Min Act: -0.0001

Data Index: 36751 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2316. Min Act: -0.0000

Data Index: 86071 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2302. Min Act: -0.0001

Data Index: 230509 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2475. Min Act: -0.0000

Data Index: 698517 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2264. Min Act: -0.0001

Data Index: 188281 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2117. Min Act: -0.0001

Data Index: 89193 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2264. Min Act: -0.0001

Data Index: 904609 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2094. Min Act: -0.0001

Data Index: 219185 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2174. Min Act: -0.0000

Data Index: 101651 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2233. Min Act: -0.0001

Data Index: 167291 (C4 (Web Text))

Max Activating Token Index: 302