Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4719 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1149051 (The Pile)

Max Activating Token Index: 749

Text #1

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.8202. Min Act: -0.0000

Data Index: 99721 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.7561. Min Act: -0.0000

Data Index: 628368 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1614151 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1091809 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.7679. Min Act: -0.0000

Data Index: 950728 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1049422 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1440166 (The Pile)

Max Activating Token Index: 907

Text #8

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6307. Min Act: -0.0000

Data Index: 221228 (The Pile)

Max Activating Token Index: 453

Text #9

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5630. Min Act: -0.0000

Data Index: 242310 (The Pile)

Max Activating Token Index: 165

Text #10

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1006662 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6192. Min Act: -0.0000

Data Index: 825611 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1341145 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5709. Min Act: -0.0000

Data Index: 545198 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6373. Min Act: -0.0000

Data Index: 269477 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5178. Min Act: -0.0000

Data Index: 50171 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1699334 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5395. Min Act: -0.0000

Data Index: 42266 (The Pile)

Max Activating Token Index: 99

Text #18

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5906. Min Act: -0.0000

Data Index: 217877 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1105045 (The Pile)

Max Activating Token Index: 112