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

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

Neuron 3251 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: 0.3462. Min Range: -0.3462

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1421704 (Python Code)

Max Activating Token Index: 414

Text #1

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2794. Min Act: -0.0000

Data Index: 983960 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1300695 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2589. Min Act: -0.0000

Data Index: 531908 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2564. Min Act: -0.0000

Data Index: 204933 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1541702 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2454. Min Act: -0.0000

Data Index: 706279 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1645783 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1608784 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1620138 (Python Code)

Max Activating Token Index: 581

Text #10

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1577870 (Python Code)

Max Activating Token Index: 57

Text #11

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2405. Min Act: -0.0000

Data Index: 196519 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1568411 (Python Code)

Max Activating Token Index: 94

Text #13

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2289. Min Act: -0.0000

Data Index: 400676 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2288. Min Act: -0.0000

Data Index: 521158 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1102081 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1484273 (Python Code)

Max Activating Token Index: 896

Text #17

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2274. Min Act: -0.0000

Data Index: 689325 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2124. Min Act: -0.0000

Data Index: 774454 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1290105 (C4 (Web Text))

Max Activating Token Index: 670