Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 6 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1016903 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0321. Min Act: -0.0003

Data Index: 261421 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0310. Min Act: -0.0003

Data Index: 113464 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0318. Min Act: -0.0003

Data Index: 948880 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0344. Min Act: -0.0003

Data Index: 359073 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1125453 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0325. Min Act: -0.0003

Data Index: 166108 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0313. Min Act: -0.0003

Data Index: 81827 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1023483 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0308. Min Act: -0.0003

Data Index: 503608 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0293. Min Act: -0.0003

Data Index: 973244 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0322. Min Act: -0.0003

Data Index: 304885 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0323. Min Act: -0.0003

Data Index: 178789 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1149503 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0300. Min Act: -0.0003

Data Index: 796919 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0288. Min Act: -0.0003

Data Index: 805047 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0299. Min Act: -0.0003

Data Index: 201056 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0311. Min Act: -0.0003

Data Index: 465759 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1131218 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0298. Min Act: -0.0003

Data Index: 950090 (C4 (Web Text))

Max Activating Token Index: 412