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

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

Neuron 3668 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: 0.0338. Min Range: -0.0338

Max Act: 0.0338. Min Act: -0.0004

Data Index: 1166176 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0325. Min Act: -0.0003

Data Index: 178874 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0288. Min Act: -0.0003

Data Index: 95991 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0321. Min Act: -0.0003

Data Index: 836471 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0294. Min Act: -0.0003

Data Index: 438042 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0321. Min Act: -0.0003

Data Index: 588012 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0303. Min Act: -0.0003

Data Index: 416157 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0326. Min Act: -0.0003

Data Index: 379586 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0293. Min Act: -0.0003

Data Index: 361198 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0267. Min Act: -0.0003

Data Index: 580808 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1429928 (Python Code)

Max Activating Token Index: 916

Text #11

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0271. Min Act: -0.0003

Data Index: 494649 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1589637 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1546266 (Python Code)

Max Activating Token Index: 599

Text #14

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1625714 (Python Code)

Max Activating Token Index: 741

Text #15

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0270. Min Act: -0.0003

Data Index: 579029 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0264. Min Act: -0.0003

Data Index: 561833 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1641272 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1307011 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0265. Min Act: -0.0003

Data Index: 464853 (C4 (Web Text))

Max Activating Token Index: 230