Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3940 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0712. Min Range: -1.0712

Max Act: 1.0459. Min Act: -0.0000

Data Index: 1155497 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9761. Min Act: -0.0000

Data Index: 306382 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 1.0712. Min Range: -1.0712

Max Act: 1.0712. Min Act: -0.0000

Data Index: 814557 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9420. Min Act: -0.0000

Data Index: 278780 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9871. Min Act: -0.0000

Data Index: 48135 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9660. Min Act: -0.0000

Data Index: 854392 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.8585. Min Act: -0.0001

Data Index: 214886 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1231034 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9350. Min Act: -0.0001

Data Index: 1237795 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9082. Min Act: -0.0000

Data Index: 532908 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9337. Min Act: -0.0000

Data Index: 205266 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.8645. Min Act: -0.0000

Data Index: 738378 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1194037 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1128535 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.8399. Min Act: -0.0000

Data Index: 870703 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1121262 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.8873. Min Act: -0.0000

Data Index: 258383 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.8392. Min Act: -0.0000

Data Index: 604588 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.9072. Min Act: -0.0000

Data Index: 730055 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.8804. Min Act: -0.0001

Data Index: 475659 (C4 (Web Text))

Max Activating Token Index: 155