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

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

Neuron 4427 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.3830. Min Act: -0.0000

Data Index: 1240151 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1104380 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1233114 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1404405 (Python Code)

Max Activating Token Index: 559

Text #4

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.5319. Min Act: -0.0000

Data Index: 295117 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.2382. Min Act: -0.0000

Data Index: 524246 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.1457. Min Act: -0.0000

Data Index: 1643061 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1488729 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.0808. Min Act: -0.0000

Data Index: 787445 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1521674 (Python Code)

Max Activating Token Index: 951

Text #10

Max Range: 1.5319. Min Range: -1.5319

Max Act: 1.0262. Min Act: -0.0000

Data Index: 875071 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 1.5319. Min Range: -1.5319

Max Act: 0.8985. Min Act: -0.0000

Data Index: 273266 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 1.5319. Min Range: -1.5319

Max Act: 0.9138. Min Act: -0.0000

Data Index: 226259 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 1.5319. Min Range: -1.5319

Max Act: 0.9440. Min Act: -0.0000

Data Index: 65176 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.5319. Min Range: -1.5319

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1313896 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.5319. Min Range: -1.5319

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1387163 (Python Code)

Max Activating Token Index: 945

Text #16

Max Range: 1.5319. Min Range: -1.5319

Max Act: 0.9887. Min Act: -0.0000

Data Index: 774953 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.5319. Min Range: -1.5319

Max Act: 0.9971. Min Act: -0.0000

Data Index: 20715 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.5319. Min Range: -1.5319

Max Act: 0.9599. Min Act: -0.0000

Data Index: 652313 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 1.5319. Min Range: -1.5319

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1259837 (C4 (Web Text))

Max Activating Token Index: 563