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

Dataset: The Pile

Neuron 1028 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: 0.4672. Min Range: -0.4672

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1083520 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1602222 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4672. Min Act: -0.0000

Data Index: 951710 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1510990 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1261769 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1814949 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1087358 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1577240 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1714178 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3288. Min Act: -0.0000

Data Index: 85760 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1482278 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1942480 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1412851 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3640. Min Act: -0.0000

Data Index: 494572 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3312. Min Act: -0.0000

Data Index: 521178 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1156249 (The Pile)

Max Activating Token Index: 983

Text #16

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3385. Min Act: -0.0000

Data Index: 622378 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1036180 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1907522 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3079. Min Act: -0.0000

Data Index: 743028 (The Pile)

Max Activating Token Index: 1005