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

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

Neuron 1013 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4431. Min Range: -4.4431

Max Act: 4.4431. Min Act: -0.0000

Data Index: 737271 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 4.4431. Min Range: -4.4431

Max Act: 4.1505. Min Act: -0.0000

Data Index: 875080 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 4.4431. Min Range: -4.4431

Max Act: 4.0947. Min Act: -0.0001

Data Index: 440816 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.9277. Min Act: -0.0001

Data Index: 1492440 (Python Code)

Max Activating Token Index: 437

Text #4

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.9780. Min Act: -0.0000

Data Index: 352461 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.6258. Min Act: -0.0001

Data Index: 762726 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.7668. Min Act: -0.0000

Data Index: 328845 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.5564. Min Act: -0.0000

Data Index: 924570 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.8241. Min Act: -0.0001

Data Index: 87311 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.1536. Min Act: -0.0000

Data Index: 874867 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.6233. Min Act: -0.0000

Data Index: 858690 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.3908. Min Act: -0.0001

Data Index: 633190 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.8547. Min Act: -0.0000

Data Index: 1391895 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.0615. Min Act: -0.0001

Data Index: 1112812 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.2690. Min Act: -0.0000

Data Index: 26745 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.5433. Min Act: -0.0001

Data Index: 270873 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.4854. Min Act: -0.0000

Data Index: 432431 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.4124. Min Act: -0.0001

Data Index: 287611 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.2475. Min Act: -0.0001

Data Index: 411041 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 4.4431. Min Range: -4.4431

Max Act: 3.1558. Min Act: -0.0000

Data Index: 1175109 (C4 (Web Text))

Max Activating Token Index: 900