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

Dataset: The Pile

Neuron 2796 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.5129. Min Act: -0.0000

Data Index: 119080 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1565359 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.5046. Min Act: -0.0000

Data Index: 200131 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1983842 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4531. Min Act: 0.0000

Data Index: 1845530 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4692. Min Act: -0.0000

Data Index: 178778 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1899666 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4610. Min Act: -0.0000

Data Index: 158732 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1779473 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1104040 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4737. Min Act: -0.0000

Data Index: 318777 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4456. Min Act: 0.0000

Data Index: 1412863 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4359. Min Act: -0.0000

Data Index: 757814 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1297379 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1302193 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1994098 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4283. Min Act: -0.0000

Data Index: 483816 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4216. Min Act: -0.0000

Data Index: 381868 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3934. Min Act: -0.0000

Data Index: 50804 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4193. Min Act: -0.0000

Data Index: 68457 (The Pile)

Max Activating Token Index: 662