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

Dataset: The Pile

Neuron 194 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0320. Min Act: -0.0000

Data Index: 986784 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0302. Min Act: -0.0000

Data Index: 748057 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0336. Min Act: -0.0001

Data Index: 162333 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0299. Min Act: -0.0000

Data Index: 1054297 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0263. Min Act: -0.0000

Data Index: 1516772 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0304. Min Act: -0.0000

Data Index: 291470 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0262. Min Act: -0.0000

Data Index: 1594556 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0260. Min Act: -0.0000

Data Index: 33886 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0262. Min Act: -0.0000

Data Index: 682024 (The Pile)

Max Activating Token Index: 607

Text #9

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0253. Min Act: -0.0000

Data Index: 1443692 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0256. Min Act: -0.0000

Data Index: 474392 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0256. Min Act: -0.0000

Data Index: 1193592 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0261. Min Act: -0.0000

Data Index: 1511181 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0247. Min Act: -0.0000

Data Index: 23812 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0251. Min Act: -0.0000

Data Index: 361708 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0259. Min Act: -0.0000

Data Index: 504451 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0253. Min Act: -0.0000

Data Index: 55513 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0253. Min Act: -0.0000

Data Index: 841612 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0252. Min Act: -0.0000

Data Index: 1280694 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0247. Min Act: -0.0000

Data Index: 435228 (The Pile)

Max Activating Token Index: 159