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

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

Neuron 1914 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.5399. Min Act: -0.0001

Data Index: 1268798 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.4096. Min Act: -0.0001

Data Index: 237045 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.3313. Min Act: -0.0001

Data Index: 387317 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.2685. Min Act: -0.0001

Data Index: 711288 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.3255. Min Act: -0.0001

Data Index: 668646 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.3234. Min Act: -0.0001

Data Index: 792106 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.3653. Min Act: -0.0001

Data Index: 526493 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.3188. Min Act: -0.0001

Data Index: 981352 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.2650. Min Act: -0.0001

Data Index: 871397 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.1830. Min Act: -0.0001

Data Index: 347286 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.2435. Min Act: -0.0001

Data Index: 541761 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.1561. Min Act: -0.0001

Data Index: 1219345 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.2204. Min Act: -0.0001

Data Index: 360452 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.1276. Min Act: -0.0001

Data Index: 320544 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.2506. Min Act: -0.0001

Data Index: 1270203 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.1829. Min Act: -0.0001

Data Index: 252127 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.1689. Min Act: -0.0001

Data Index: 1099487 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.1568. Min Act: -0.0001

Data Index: 1086718 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.1585. Min Act: -0.0001

Data Index: 240992 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.5399. Min Range: -1.5399

Max Act: 1.1410. Min Act: -0.0001

Data Index: 1087502 (C4 (Web Text))

Max Activating Token Index: 887