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

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

Neuron 631 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.4338. Min Act: -0.0000

Data Index: 1589860 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.8157. Min Act: -0.0000

Data Index: 1073987 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3359. Min Act: -0.0000

Data Index: 1623997 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.5804. Min Act: -0.0000

Data Index: 1599073 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3153. Min Act: -0.0000

Data Index: 1361962 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3295. Min Act: -0.0000

Data Index: 1605085 (Python Code)

Max Activating Token Index: 790

Text #6

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3965. Min Act: -0.0000

Data Index: 1407345 (Python Code)

Max Activating Token Index: 941

Text #7

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.2702. Min Act: -0.0000

Data Index: 1509919 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.4475. Min Act: -0.0000

Data Index: 1455937 (Python Code)

Max Activating Token Index: 495

Text #9

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3198. Min Act: -0.0000

Data Index: 1416373 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.2772. Min Act: -0.0000

Data Index: 1608612 (Python Code)

Max Activating Token Index: 392

Text #11

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.2758. Min Act: -0.0000

Data Index: 1630694 (Python Code)

Max Activating Token Index: 361

Text #12

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.0269. Min Act: -0.0000

Data Index: 1368457 (Python Code)

Max Activating Token Index: 265

Text #13

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.2372. Min Act: -0.0000

Data Index: 1375699 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.0823. Min Act: -0.0000

Data Index: 662946 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3425. Min Act: -0.0000

Data Index: 1471403 (Python Code)

Max Activating Token Index: 724

Text #16

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.2311. Min Act: -0.0000

Data Index: 1518230 (Python Code)

Max Activating Token Index: 418

Text #17

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.1666. Min Act: -0.0000

Data Index: 1565383 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3035. Min Act: -0.0000

Data Index: 1505393 (Python Code)

Max Activating Token Index: 583

Text #19

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.1627. Min Act: -0.0000

Data Index: 1467283 (Python Code)

Max Activating Token Index: 563