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

Dataset: The Pile

Neuron 966 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 19 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 246 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 231 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 109 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 111 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 358 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 217 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 325 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 193 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 196 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 4 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 320 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 189 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 326 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 170 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 150 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 155 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 85 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 149 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 1 (The Pile)

Max Activating Token Index: 1