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

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

Neuron 3475 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: 2.6959. Min Range: -2.6959

Max Act: 2.6959. Min Act: -0.0000

Data Index: 754611 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.6759. Min Act: -0.0000

Data Index: 783508 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.4746. Min Act: -0.0000

Data Index: 927659 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.4123. Min Act: -0.0000

Data Index: 972118 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.3017. Min Act: -0.0000

Data Index: 1325712 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.2450. Min Act: -0.0000

Data Index: 1018757 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.1293. Min Act: -0.0000

Data Index: 1292986 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.3328. Min Act: -0.0000

Data Index: 586831 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.3067. Min Act: -0.0000

Data Index: 797485 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.1413. Min Act: -0.0000

Data Index: 788423 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 2.6959. Min Range: -2.6959

Max Act: 1.9969. Min Act: -0.0000

Data Index: 1296543 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.0939. Min Act: -0.0000

Data Index: 1013203 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.0937. Min Act: -0.0000

Data Index: 357421 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.0807. Min Act: -0.0000

Data Index: 1056729 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.0687. Min Act: -0.0000

Data Index: 1003794 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.0567. Min Act: -0.0000

Data Index: 854749 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.0480. Min Act: -0.0000

Data Index: 1183790 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.1586. Min Act: -0.0000

Data Index: 591110 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.0389. Min Act: -0.0000

Data Index: 1063450 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 2.6959. Min Range: -2.6959

Max Act: 2.1432. Min Act: -0.0000

Data Index: 1296643 (C4 (Web Text))

Max Activating Token Index: 803