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

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

Neuron 71 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1097485 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0514. Min Act: -0.0001

Data Index: 790787 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0492. Min Act: -0.0001

Data Index: 970575 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0423. Min Act: -0.0001

Data Index: 614371 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0380. Min Act: -0.0001

Data Index: 1284397 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0385. Min Act: -0.0001

Data Index: 170668 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0329. Min Act: -0.0001

Data Index: 47330 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1185200 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0329. Min Act: -0.0001

Data Index: 802305 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0327. Min Act: -0.0001

Data Index: 840326 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1213340 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1138999 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0278. Min Act: -0.0001

Data Index: 478261 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0391. Min Act: -0.0001

Data Index: 299848 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0374. Min Act: -0.0001

Data Index: 544462 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1154335 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1065726 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1166737 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0362. Min Act: -0.0001

Data Index: 981608 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0331. Min Act: -0.0001

Data Index: 586289 (C4 (Web Text))

Max Activating Token Index: 1015