Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1973 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.3149. Min Act: -0.0003

Data Index: 1128813 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2715. Min Act: -0.0003

Data Index: 636535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2615. Min Act: -0.0003

Data Index: 111414 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2548. Min Act: -0.0003

Data Index: 1292795 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2620. Min Act: -0.0003

Data Index: 868968 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2531. Min Act: -0.0003

Data Index: 23033 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2417. Min Act: -0.0003

Data Index: 543464 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2501. Min Act: -0.0003

Data Index: 3272 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2499. Min Act: -0.0003

Data Index: 346984 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2452. Min Act: -0.0003

Data Index: 1118095 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2418. Min Act: -0.0003

Data Index: 628220 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2402. Min Act: -0.0003

Data Index: 735156 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2382. Min Act: -0.0003

Data Index: 299703 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2310. Min Act: -0.0003

Data Index: 32771 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2360. Min Act: -0.0003

Data Index: 434594 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2356. Min Act: -0.0003

Data Index: 417750 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2312. Min Act: -0.0003

Data Index: 428259 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2279. Min Act: -0.0003

Data Index: 509184 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2355. Min Act: -0.0003

Data Index: 1084005 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2266. Min Act: -0.0003

Data Index: 1199474 (C4 (Web Text))

Max Activating Token Index: 401