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

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

Neuron 1707 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: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0002

Data Index: 182414 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0557. Min Act: -0.0002

Data Index: 740573 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0472. Min Act: -0.0002

Data Index: 915969 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1345381 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0406. Min Act: -0.0002

Data Index: 306439 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0429. Min Act: -0.0002

Data Index: 983984 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0376. Min Act: -0.0002

Data Index: 104853 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1005225 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0409. Min Act: -0.0002

Data Index: 860403 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0373. Min Act: -0.0002

Data Index: 673517 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0372. Min Act: -0.0002

Data Index: 78271 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0383. Min Act: -0.0002

Data Index: 126115 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1002398 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0380. Min Act: -0.0002

Data Index: 741448 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0372. Min Act: -0.0002

Data Index: 714725 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0371. Min Act: -0.0002

Data Index: 197139 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1156705 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1321542 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0338. Min Act: -0.0002

Data Index: 938796 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0350. Min Act: -0.0002

Data Index: 888157 (C4 (Web Text))

Max Activating Token Index: 589