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

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

Neuron 1464 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: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1296447 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0440. Min Act: -0.0003

Data Index: 361402 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1241669 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0426. Min Act: -0.0003

Data Index: 888523 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1002818 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0442. Min Act: -0.0003

Data Index: 953462 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0368. Min Act: -0.0003

Data Index: 775533 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0351. Min Act: -0.0003

Data Index: 816038 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0391. Min Act: -0.0003

Data Index: 684916 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0404. Min Act: -0.0003

Data Index: 660120 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0389. Min Act: -0.0003

Data Index: 808998 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0329. Min Act: -0.0003

Data Index: 154771 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0313. Min Act: -0.0003

Data Index: 737973 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0383. Min Act: -0.0003

Data Index: 85046 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0379. Min Act: -0.0003

Data Index: 959626 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0375. Min Act: -0.0003

Data Index: 455186 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0390. Min Act: -0.0003

Data Index: 907509 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0358. Min Act: -0.0003

Data Index: 976272 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1633375 (Python Code)

Max Activating Token Index: 768

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1248118 (C4 (Web Text))

Max Activating Token Index: 75