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

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

Neuron 4150 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1053936 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.9381. Min Act: -0.0000

Data Index: 244425 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.9120. Min Act: -0.0000

Data Index: 924340 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1314659 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1042760 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.8363. Min Act: -0.0000

Data Index: 961631 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.8126. Min Act: -0.0000

Data Index: 723432 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.8350. Min Act: -0.0000

Data Index: 834130 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.8156. Min Act: -0.0000

Data Index: 152625 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.8201. Min Act: -0.0000

Data Index: 220743 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.8209. Min Act: -0.0000

Data Index: 954235 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1391633 (Python Code)

Max Activating Token Index: 248

Text #12

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1314113 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.7456. Min Act: -0.0000

Data Index: 798782 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.7537. Min Act: -0.0000

Data Index: 832797 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.7282. Min Act: 0.0000

Data Index: 685169 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.7595. Min Act: -0.0000

Data Index: 912117 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.7160. Min Act: -0.0000

Data Index: 307191 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.7200. Min Act: -0.0000

Data Index: 749445 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.9381. Min Range: -0.9381

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1156147 (C4 (Web Text))

Max Activating Token Index: 358