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

Dataset: The Pile

Neuron 3362 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: 0.2906. Min Range: -0.2906

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1223296 (The Pile)

Max Activating Token Index: 224

Text #1

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2559. Min Act: -0.0000

Data Index: 944497 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1581998 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1758636 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2490. Min Act: -0.0000

Data Index: 852482 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2397. Min Act: -0.0000

Data Index: 402708 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1909506 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1044756 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2287. Min Act: -0.0000

Data Index: 901762 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1990685 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1619733 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1530109 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1066550 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2261. Min Act: -0.0000

Data Index: 324579 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1553574 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2401. Min Act: -0.0000

Data Index: 789058 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1826433 (The Pile)

Max Activating Token Index: 71

Text #17

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2157. Min Act: -0.0000

Data Index: 999620 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1785828 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2133. Min Act: -0.0000

Data Index: 117280 (The Pile)

Max Activating Token Index: 353