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

Dataset: The Pile

Neuron 456 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.6187. Min Act: -0.0000

Data Index: 374941 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.8201. Min Act: -0.0000

Data Index: 1811394 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.5060. Min Act: -0.0000

Data Index: 1952232 (The Pile)

Max Activating Token Index: 886

Text #3

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.4395. Min Act: -0.0000

Data Index: 401476 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.1318. Min Act: -0.0000

Data Index: 208374 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.2523. Min Act: -0.0000

Data Index: 349149 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.2233. Min Act: -0.0000

Data Index: 309077 (The Pile)

Max Activating Token Index: 667

Text #7

Max Range: 3.8201. Min Range: -3.8201

Max Act: 2.9913. Min Act: -0.0000

Data Index: 1392476 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 3.8201. Min Range: -3.8201

Max Act: 2.7976. Min Act: -0.0000

Data Index: 1687182 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.0425. Min Act: -0.0000

Data Index: 1580268 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.0087. Min Act: -0.0000

Data Index: 243449 (The Pile)

Max Activating Token Index: 659

Text #11

Max Range: 3.8201. Min Range: -3.8201

Max Act: 2.8690. Min Act: -0.0000

Data Index: 1390289 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.1140. Min Act: -0.0000

Data Index: 438752 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 3.8201. Min Range: -3.8201

Max Act: 2.8767. Min Act: -0.0000

Data Index: 1155601 (The Pile)

Max Activating Token Index: 429

Text #14

Max Range: 3.8201. Min Range: -3.8201

Max Act: 2.8744. Min Act: -0.0000

Data Index: 506990 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.0058. Min Act: -0.0000

Data Index: 1260450 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 3.8201. Min Range: -3.8201

Max Act: 2.8789. Min Act: -0.0000

Data Index: 1276909 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 3.8201. Min Range: -3.8201

Max Act: 2.7585. Min Act: -0.0000

Data Index: 852662 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 3.8201. Min Range: -3.8201

Max Act: 2.7444. Min Act: -0.0000

Data Index: 206592 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 3.8201. Min Range: -3.8201

Max Act: 2.7189. Min Act: -0.0000

Data Index: 660130 (The Pile)

Max Activating Token Index: 590