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

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

Neuron 4261 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.4145. Min Act: -0.0000

Data Index: 465499 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1539238 (Python Code)

Max Activating Token Index: 410

Text #2

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1461411 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1651725 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1409965 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1394112 (Python Code)

Max Activating Token Index: 930

Text #6

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1426624 (Python Code)

Max Activating Token Index: 734

Text #7

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2677. Min Act: -0.0000

Data Index: 489098 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1546220 (Python Code)

Max Activating Token Index: 626

Text #9

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1591496 (Python Code)

Max Activating Token Index: 880

Text #10

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1482488 (Python Code)

Max Activating Token Index: 173

Text #11

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1624483 (Python Code)

Max Activating Token Index: 983

Text #12

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1467645 (Python Code)

Max Activating Token Index: 689

Text #13

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1372162 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1471018 (Python Code)

Max Activating Token Index: 208

Text #15

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1212430 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2276. Min Act: -0.0000

Data Index: 1463927 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1436676 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1044916 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.4145. Min Range: -0.4145

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1367606 (Python Code)

Max Activating Token Index: 927