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

Dataset: The Pile

Neuron 461 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1450746 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1231261 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1624871 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4564. Min Act: -0.0000

Data Index: 506167 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1202019 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1609528 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1123718 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4139. Min Act: -0.0000

Data Index: 748491 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4062. Min Act: -0.0000

Data Index: 387170 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1852803 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3891. Min Act: -0.0000

Data Index: 596731 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3827. Min Act: -0.0000

Data Index: 660520 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3761. Min Act: -0.0000

Data Index: 870805 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4209. Min Act: -0.0000

Data Index: 615034 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1185669 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1362097 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3914. Min Act: -0.0000

Data Index: 86526 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1512463 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1664659 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1714653 (The Pile)

Max Activating Token Index: 971