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

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

Neuron 4141 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.6735. Min Act: -0.0000

Data Index: 46450 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1041372 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.6020. Min Act: -0.0000

Data Index: 817502 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1308654 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.6264. Min Act: -0.0000

Data Index: 723518 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1303862 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.5880. Min Act: -0.0000

Data Index: 794783 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.5805. Min Act: -0.0000

Data Index: 535977 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.5191. Min Act: -0.0000

Data Index: 692937 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.4944. Min Act: -0.0000

Data Index: 244829 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.4968. Min Act: -0.0000

Data Index: 422022 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.4576. Min Act: -0.0000

Data Index: 88835 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1561616 (Python Code)

Max Activating Token Index: 355

Text #13

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.4437. Min Act: -0.0000

Data Index: 594389 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1015323 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1432417 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.4042. Min Act: -0.0000

Data Index: 964601 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1072947 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.3996. Min Act: -0.0000

Data Index: 179778 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.6735. Min Range: -0.6735

Max Act: 0.3932. Min Act: -0.0000

Data Index: 20725 (C4 (Web Text))

Max Activating Token Index: 448