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

Dataset: The Pile

Neuron 775 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7531. Min Act: -0.0000

Data Index: 535468 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7208. Min Act: -0.0000

Data Index: 145335 (The Pile)

Max Activating Token Index: 862

Text #2

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7329. Min Act: -0.0000

Data Index: 804742 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1368643 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1357774 (The Pile)

Max Activating Token Index: 506

Text #5

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7228. Min Act: 0.0000

Data Index: 30082 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1941733 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1854078 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6905. Min Act: -0.0000

Data Index: 341293 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6774. Min Act: -0.0000

Data Index: 275145 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6883. Min Act: -0.0000

Data Index: 404351 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6134. Min Act: -0.0000

Data Index: 748021 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6261. Min Act: 0.0000

Data Index: 1510386 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6193. Min Act: 0.0000

Data Index: 1868888 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6383. Min Act: -0.0000

Data Index: 414806 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1611309 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6852. Min Act: -0.0000

Data Index: 998405 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6385. Min Act: -0.0000

Data Index: 265966 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1080385 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6245. Min Act: -0.0000

Data Index: 702018 (The Pile)

Max Activating Token Index: 173