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

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

Neuron 54 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.8364. Min Act: -0.0000

Data Index: 276482 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.8935. Min Act: -0.0000

Data Index: 549652 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.8971. Min Act: -0.0000

Data Index: 467975 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.6772. Min Act: -0.0000

Data Index: 813463 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.5110. Min Act: -0.0000

Data Index: 524749 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.4611. Min Act: -0.0000

Data Index: 1175382 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.3922. Min Act: -0.0000

Data Index: 1468359 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.6150. Min Act: -0.0000

Data Index: 746580 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.2247. Min Act: -0.0000

Data Index: 1504992 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.3409. Min Act: -0.0000

Data Index: 279865 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.2729. Min Act: -0.0000

Data Index: 737718 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.2528. Min Act: -0.0000

Data Index: 660109 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.1367. Min Act: -0.0000

Data Index: 14493 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.2374. Min Act: -0.0000

Data Index: 764520 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.1926. Min Act: -0.0000

Data Index: 149519 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.1730. Min Act: -0.0000

Data Index: 1039657 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.2583. Min Act: -0.0000

Data Index: 574607 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.1368. Min Act: -0.0000

Data Index: 432035 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.2506. Min Act: -0.0000

Data Index: 791378 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.0212. Min Act: -0.0000

Data Index: 505929 (C4 (Web Text))

Max Activating Token Index: 741