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

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

Neuron 2334 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4351. Min Act: -0.0000

Data Index: 470565 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3985. Min Act: -0.0000

Data Index: 35828 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3639. Min Act: -0.0000

Data Index: 603101 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1352299 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2974. Min Act: -0.0000

Data Index: 904185 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2923. Min Act: -0.0000

Data Index: 779078 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2907. Min Act: -0.0000

Data Index: 917935 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3228. Min Act: -0.0001

Data Index: 705826 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1202655 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2871. Min Act: -0.0000

Data Index: 529729 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2379. Min Act: -0.0000

Data Index: 470086 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2457. Min Act: -0.0001

Data Index: 996048 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2337. Min Act: -0.0001

Data Index: 242023 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2278. Min Act: -0.0000

Data Index: 974875 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2294. Min Act: -0.0000

Data Index: 494634 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1080159 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2034. Min Act: -0.0000

Data Index: 591514 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2246. Min Act: -0.0000

Data Index: 825640 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1154559 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2049. Min Act: -0.0000

Data Index: 824678 (C4 (Web Text))

Max Activating Token Index: 832