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

Dataset: The Pile

Neuron 3197 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: 0.8898. Min Range: -0.8898

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1725053 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8329. Min Act: -0.0000

Data Index: 208589 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1908236 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1978046 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7922. Min Act: -0.0000

Data Index: 210556 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8061. Min Act: -0.0000

Data Index: 387137 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1231178 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8151. Min Act: -0.0000

Data Index: 437056 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8242. Min Act: -0.0000

Data Index: 590146 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1859378 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1140738 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8237. Min Act: -0.0000

Data Index: 75252 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1571388 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1821382 (The Pile)

Max Activating Token Index: 343

Text #14

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8072. Min Act: -0.0000

Data Index: 1659372 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1297946 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1338511 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1071534 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7467. Min Act: -0.0000

Data Index: 127214 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6956. Min Act: -0.0000

Data Index: 669201 (The Pile)

Max Activating Token Index: 138