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

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

Neuron 3372 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: 0.3920. Min Range: -0.3920

Max Act: 0.3920. Min Act: -0.0000

Data Index: 633495 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.3449. Min Act: -0.0000

Data Index: 538730 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.3194. Min Act: -0.0000

Data Index: 665768 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1046285 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2667. Min Act: -0.0000

Data Index: 27604 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2785. Min Act: -0.0000

Data Index: 118725 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2657. Min Act: -0.0000

Data Index: 830833 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2354. Min Act: -0.0000

Data Index: 444982 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1430232 (Python Code)

Max Activating Token Index: 157

Text #9

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1411732 (Python Code)

Max Activating Token Index: 298

Text #10

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2351. Min Act: -0.0000

Data Index: 975641 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1448601 (Python Code)

Max Activating Token Index: 179

Text #12

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1621281 (Python Code)

Max Activating Token Index: 984

Text #13

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2239. Min Act: -0.0000

Data Index: 339600 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1578076 (Python Code)

Max Activating Token Index: 341

Text #15

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2358. Min Act: -0.0000

Data Index: 22245 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1520874 (Python Code)

Max Activating Token Index: 917

Text #17

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1194091 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2234. Min Act: -0.0000

Data Index: 336865 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.3920. Min Range: -0.3920

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1369886 (Python Code)

Max Activating Token Index: 336