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

Dataset: The Pile

Neuron 4838 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.3275. Min Act: -0.0000

Data Index: 810430 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1373852 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1504764 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2556. Min Act: -0.0000

Data Index: 299762 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2585. Min Act: -0.0000

Data Index: 990663 (The Pile)

Max Activating Token Index: 954

Text #5

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2624. Min Act: -0.0000

Data Index: 32612 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1577331 (The Pile)

Max Activating Token Index: 539

Text #7

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2511. Min Act: -0.0000

Data Index: 265483 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1191159 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2443. Min Act: -0.0000

Data Index: 193791 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2279. Min Act: -0.0000

Data Index: 849469 (The Pile)

Max Activating Token Index: 234

Text #11

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2351. Min Act: -0.0000

Data Index: 926282 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1273335 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1250654 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2358. Min Act: -0.0000

Data Index: 481364 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2388. Min Act: -0.0000

Data Index: 457433 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1231163 (The Pile)

Max Activating Token Index: 795

Text #17

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2422. Min Act: -0.0000

Data Index: 510266 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1214030 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2218. Min Act: -0.0000

Data Index: 368189 (The Pile)

Max Activating Token Index: 559