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

Dataset: The Pile

Neuron 1405 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: 0.3484. Min Range: -0.3484

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1736653 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1708104 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1272412 (The Pile)

Max Activating Token Index: 619

Text #3

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.3000. Min Act: -0.0000

Data Index: 159318 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1090673 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1460730 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1592688 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2433. Min Act: -0.0000

Data Index: 261046 (The Pile)

Max Activating Token Index: 62

Text #8

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1387100 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1495389 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1821936 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1098275 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2489. Min Act: -0.0000

Data Index: 487832 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1459329 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2595. Min Act: -0.0000

Data Index: 929619 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1585834 (The Pile)

Max Activating Token Index: 923

Text #16

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1993415 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1233191 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1848924 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 0.3484. Min Range: -0.3484

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1964482 (The Pile)

Max Activating Token Index: 811