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

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

Neuron 2525 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.8245. Min Act: -0.0000

Data Index: 120643 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.7493. Min Act: -0.0000

Data Index: 1300411 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.7267. Min Act: -0.0000

Data Index: 961210 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.6138. Min Act: 0.0000

Data Index: 128846 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1235589 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.3529. Min Act: -0.0000

Data Index: 126425 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2520. Min Act: -0.0000

Data Index: 296235 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1137248 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1051102 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2388. Min Act: -0.0000

Data Index: 622280 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.1495. Min Act: -0.0000

Data Index: 466896 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2206. Min Act: -0.0000

Data Index: 567667 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2174. Min Act: 0.0001

Data Index: 668721 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1037173 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.1971. Min Act: -0.0000

Data Index: 687714 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2689. Min Act: -0.0000

Data Index: 892608 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1256531 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.1552. Min Act: -0.0000

Data Index: 623567 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.1399. Min Act: -0.0000

Data Index: 114384 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.1212. Min Act: -0.0000

Data Index: 470321 (C4 (Web Text))

Max Activating Token Index: 163