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

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

Neuron 3981 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: 2.4843. Min Range: -2.4843

Max Act: 2.4843. Min Act: -0.0000

Data Index: 561852 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 2.4843. Min Range: -2.4843

Max Act: 2.4384. Min Act: -0.0000

Data Index: 1169617 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 2.4843. Min Range: -2.4843

Max Act: 2.3719. Min Act: -0.0000

Data Index: 1042551 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 2.4843. Min Range: -2.4843

Max Act: 2.1313. Min Act: -0.0000

Data Index: 482362 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.7664. Min Act: -0.0000

Data Index: 1256998 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.8282. Min Act: -0.0000

Data Index: 240467 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.7744. Min Act: -0.0000

Data Index: 267313 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.5897. Min Act: -0.0000

Data Index: 1242388 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.5319. Min Act: -0.0000

Data Index: 550042 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.5448. Min Act: -0.0000

Data Index: 1012482 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.5816. Min Act: -0.0000

Data Index: 217932 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.4230. Min Act: -0.0000

Data Index: 579206 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.5818. Min Act: -0.0000

Data Index: 932451 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.4829. Min Act: -0.0000

Data Index: 64392 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.6386. Min Act: -0.0000

Data Index: 1003323 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.5259. Min Act: -0.0000

Data Index: 39196 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.4341. Min Act: -0.0000

Data Index: 452866 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.5215. Min Act: -0.0000

Data Index: 829792 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.6783. Min Act: -0.0000

Data Index: 1321817 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 2.4843. Min Range: -2.4843

Max Act: 1.4873. Min Act: -0.0000

Data Index: 943825 (C4 (Web Text))

Max Activating Token Index: 891