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

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

Neuron 998 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: 0.0393. Min Range: -0.0393

Max Act: 0.0393. Min Act: -0.0003

Data Index: 610245 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0298. Min Act: -0.0003

Data Index: 179334 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0338. Min Act: -0.0004

Data Index: 718628 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0374. Min Act: -0.0003

Data Index: 751371 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0341. Min Act: -0.0003

Data Index: 320256 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0351. Min Act: -0.0003

Data Index: 741236 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0350. Min Act: -0.0003

Data Index: 1432853 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0331. Min Act: -0.0003

Data Index: 468054 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1532103 (Python Code)

Max Activating Token Index: 544

Text #9

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0347. Min Act: -0.0003

Data Index: 361371 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1226041 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1472473 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0353. Min Act: -0.0003

Data Index: 531244 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1044732 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0331. Min Act: -0.0003

Data Index: 564169 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0334. Min Act: -0.0003

Data Index: 100940 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0315. Min Act: -0.0003

Data Index: 100817 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0301. Min Act: -0.0003

Data Index: 321093 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0289. Min Act: -0.0003

Data Index: 902184 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0290. Min Act: -0.0003

Data Index: 109409 (C4 (Web Text))

Max Activating Token Index: 150