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

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

Neuron 2651 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.5241. Min Act: -0.0000

Data Index: 18066 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.6395. Min Act: -0.0000

Data Index: 814541 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.5846. Min Act: -0.0000

Data Index: 695396 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.3552. Min Act: -0.0000

Data Index: 310423 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.3223. Min Act: -0.0000

Data Index: 1073323 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1651129 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.2740. Min Act: -0.0000

Data Index: 512017 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.2639. Min Act: -0.0000

Data Index: 1090318 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1142757 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1603015 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1552043 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1636202 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1433101 (Python Code)

Max Activating Token Index: 455

Text #13

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.2766. Min Act: -0.0000

Data Index: 199640 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.3023. Min Act: -0.0000

Data Index: 347734 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.2148. Min Act: -0.0000

Data Index: 934845 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.2501. Min Act: -0.0000

Data Index: 512149 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.2343. Min Act: -0.0000

Data Index: 609189 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.1623. Min Act: -0.0000

Data Index: 755768 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 1.6395. Min Range: -1.6395

Max Act: 1.2605. Min Act: -0.0000

Data Index: 777016 (C4 (Web Text))

Max Activating Token Index: 196