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

Dataset: The Pile

Neuron 870 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: 0.3381. Min Range: -0.3381

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1685416 (The Pile)

Max Activating Token Index: 383

Text #1

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.3360. Min Act: -0.0000

Data Index: 301683 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1531182 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2977. Min Act: -0.0000

Data Index: 685410 (The Pile)

Max Activating Token Index: 664

Text #4

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.3157. Min Act: -0.0000

Data Index: 29183 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2816. Min Act: -0.0000

Data Index: 807869 (The Pile)

Max Activating Token Index: 721

Text #6

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.3007. Min Act: -0.0000

Data Index: 12673 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1746225 (The Pile)

Max Activating Token Index: 202

Text #8

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2871. Min Act: -0.0000

Data Index: 363167 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1796935 (The Pile)

Max Activating Token Index: 305

Text #10

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1874545 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1061204 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2991. Min Act: -0.0000

Data Index: 240197 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2878. Min Act: -0.0000

Data Index: 316992 (The Pile)

Max Activating Token Index: 440

Text #14

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1021935 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2675. Min Act: -0.0000

Data Index: 649244 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2835. Min Act: -0.0000

Data Index: 686799 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2951. Min Act: -0.0000

Data Index: 370156 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2741. Min Act: -0.0000

Data Index: 467312 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 0.3381. Min Range: -0.3381

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1198331 (The Pile)

Max Activating Token Index: 88