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

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

Neuron 4756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.6277. Min Act: -0.0000

Data Index: 681681 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.3446. Min Act: -0.0000

Data Index: 448817 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.4039. Min Act: -0.0000

Data Index: 940426 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.3259. Min Act: -0.0000

Data Index: 771530 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.3169. Min Act: -0.0000

Data Index: 916798 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.0636. Min Act: -0.0000

Data Index: 830457 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.1769. Min Act: -0.0000

Data Index: 897810 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.3190. Min Act: -0.0000

Data Index: 501423 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.0028. Min Act: -0.0000

Data Index: 1020152 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.1453. Min Act: -0.0000

Data Index: 922810 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.1098. Min Act: -0.0000

Data Index: 584087 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 3.6277. Min Range: -3.6277

Max Act: 2.9270. Min Act: -0.0000

Data Index: 24440 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.0822. Min Act: -0.0000

Data Index: 211320 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.0512. Min Act: -0.0000

Data Index: 1141856 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 3.6277. Min Range: -3.6277

Max Act: 2.8777. Min Act: -0.0000

Data Index: 34455 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 3.6277. Min Range: -3.6277

Max Act: 2.9823. Min Act: -0.0000

Data Index: 884455 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 3.6277. Min Range: -3.6277

Max Act: 2.9733. Min Act: -0.0000

Data Index: 811982 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 3.6277. Min Range: -3.6277

Max Act: 2.9452. Min Act: -0.0000

Data Index: 453100 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 3.6277. Min Range: -3.6277

Max Act: 2.9288. Min Act: -0.0000

Data Index: 121707 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.6277. Min Range: -3.6277

Max Act: 2.9037. Min Act: -0.0000

Data Index: 766536 (C4 (Web Text))

Max Activating Token Index: 652