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

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

Neuron 3765 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0002

Data Index: 387368 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0448. Min Act: -0.0002

Data Index: 794374 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1159619 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0417. Min Act: -0.0002

Data Index: 524592 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1126029 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0374. Min Act: -0.0002

Data Index: 325197 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1140262 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0382. Min Act: -0.0002

Data Index: 975112 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0378. Min Act: -0.0002

Data Index: 166182 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0366. Min Act: -0.0002

Data Index: 578461 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0356. Min Act: -0.0002

Data Index: 226786 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0343. Min Act: -0.0002

Data Index: 832404 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0362. Min Act: -0.0002

Data Index: 33939 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0335. Min Act: -0.0002

Data Index: 76683 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0355. Min Act: -0.0002

Data Index: 153800 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1274150 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1020116 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0342. Min Act: -0.0002

Data Index: 491956 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0328. Min Act: -0.0002

Data Index: 534266 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0330. Min Act: -0.0002

Data Index: 71544 (C4 (Web Text))

Max Activating Token Index: 40