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

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

Neuron 38 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0003

Data Index: 213291 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0295. Min Act: -0.0003

Data Index: 762800 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0289. Min Act: -0.0003

Data Index: 830262 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0286. Min Act: -0.0003

Data Index: 32618 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0288. Min Act: -0.0003

Data Index: 210718 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0255. Min Act: -0.0003

Data Index: 815780 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0279. Min Act: -0.0003

Data Index: 684895 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0284. Min Act: -0.0003

Data Index: 685138 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1347224 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0264. Min Act: -0.0003

Data Index: 652585 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1569846 (Python Code)

Max Activating Token Index: 407

Text #11

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1252822 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0262. Min Act: -0.0003

Data Index: 906530 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1656119 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0270. Min Act: -0.0003

Data Index: 34001 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0255. Min Act: -0.0003

Data Index: 167130 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1523227 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0264. Min Act: -0.0003

Data Index: 868368 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1507577 (Python Code)

Max Activating Token Index: 224

Text #19

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 886