Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 977 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.9373. Min Act: -0.0000

Data Index: 245633 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.5028. Min Act: -0.0000

Data Index: 943386 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.5745. Min Act: -0.0000

Data Index: 1033930 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.6820. Min Act: -0.0000

Data Index: 381203 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.6206. Min Act: -0.0000

Data Index: 933178 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.3475. Min Act: -0.0000

Data Index: 1046241 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.3690. Min Act: -0.0000

Data Index: 567906 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.3454. Min Act: -0.0000

Data Index: 1129323 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.3323. Min Act: -0.0000

Data Index: 541934 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.1774. Min Act: -0.0000

Data Index: 1046848 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.1963. Min Act: -0.0000

Data Index: 418242 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.1776. Min Act: -0.0000

Data Index: 795353 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.1469. Min Act: -0.0000

Data Index: 1568247 (Python Code)

Max Activating Token Index: 694

Text #13

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.1421. Min Act: -0.0000

Data Index: 1128167 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 2.9373. Min Range: -2.9373

Max Act: 1.9643. Min Act: -0.0000

Data Index: 275488 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 2.9373. Min Range: -2.9373

Max Act: 1.9901. Min Act: -0.0000

Data Index: 937890 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 2.9373. Min Range: -2.9373

Max Act: 1.9426. Min Act: -0.0000

Data Index: 1011853 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.0533. Min Act: -0.0000

Data Index: 266723 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 2.9373. Min Range: -2.9373

Max Act: 1.9333. Min Act: -0.0000

Data Index: 1184310 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.0245. Min Act: -0.0000

Data Index: 940973 (C4 (Web Text))

Max Activating Token Index: 355