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

Dataset: The Pile

Neuron 782 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.2129. Min Act: -0.0000

Data Index: 251145 (The Pile)

Max Activating Token Index: 816

Text #1

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.1655. Min Act: -0.0000

Data Index: 52179 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8909. Min Act: -0.0000

Data Index: 245515 (The Pile)

Max Activating Token Index: 954

Text #3

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.0647. Min Act: -0.0000

Data Index: 786288 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.0266. Min Act: -0.0000

Data Index: 459483 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.0166. Min Act: -0.0000

Data Index: 475336 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1061152 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1884656 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9190. Min Act: -0.0000

Data Index: 63575 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9126. Min Act: -0.0000

Data Index: 520911 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1541494 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8425. Min Act: -0.0000

Data Index: 724193 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9370. Min Act: -0.0000

Data Index: 987001 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8697. Min Act: -0.0000

Data Index: 228763 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.9817. Min Act: -0.0000

Data Index: 559187 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1152896 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1821613 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1828004 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.2129. Min Range: -1.2129

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1154176 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 1.2129. Min Range: -1.2129

Max Act: 0.8848. Min Act: -0.0000

Data Index: 864037 (The Pile)

Max Activating Token Index: 379