Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1845 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.7192. Min Act: -0.0000

Data Index: 391233 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.6723. Min Act: -0.0000

Data Index: 856184 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.6475. Min Act: -0.0000

Data Index: 381874 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5452. Min Act: -0.0000

Data Index: 414135 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1423215 (Python Code)

Max Activating Token Index: 497

Text #5

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5580. Min Act: 0.0000

Data Index: 193237 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5406. Min Act: -0.0000

Data Index: 653371 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1178720 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1560667 (Python Code)

Max Activating Token Index: 892

Text #9

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1222399 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1121623 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5314. Min Act: -0.0000

Data Index: 222310 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1641573 (Python Code)

Max Activating Token Index: 926

Text #13

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1050711 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.4860. Min Act: -0.0000

Data Index: 818012 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1040039 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5170. Min Act: -0.0000

Data Index: 933749 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1217954 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1484635 (Python Code)

Max Activating Token Index: 909

Text #19

Max Range: 0.7192. Min Range: -0.7192

Max Act: 0.4785. Min Act: -0.0000

Data Index: 224222 (C4 (Web Text))

Max Activating Token Index: 594