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

Dataset: The Pile

Neuron 1486 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3769. Min Act: -0.0000

Data Index: 990298 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1205805 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2673. Min Act: -0.0000

Data Index: 656662 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2883. Min Act: -0.0000

Data Index: 37654 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1141258 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2781. Min Act: -0.0000

Data Index: 58412 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2484. Min Act: -0.0000

Data Index: 635829 (The Pile)

Max Activating Token Index: 398

Text #7

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1300269 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2482. Min Act: -0.0000

Data Index: 74426 (The Pile)

Max Activating Token Index: 467

Text #9

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1288183 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2562. Min Act: -0.0000

Data Index: 132660 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2371. Min Act: -0.0000

Data Index: 65819 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1520559 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1381931 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1669101 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1352437 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1940857 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1164818 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1840736 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 0.3769. Min Range: -0.3769

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1901836 (The Pile)

Max Activating Token Index: 667