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

Dataset: The Pile

Neuron 1869 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: 0.4501. Min Range: -0.4501

Max Act: 0.4146. Min Act: -0.0000

Data Index: 175048 (The Pile)

Max Activating Token Index: 308

Text #1

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3856. Min Act: -0.0000

Data Index: 370499 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1346245 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1825012 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1703099 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1402052 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1488889 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1964089 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3422. Min Act: -0.0000

Data Index: 738622 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3823. Min Act: -0.0000

Data Index: 339159 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1895496 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3841. Min Act: -0.0000

Data Index: 863940 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3555. Min Act: -0.0000

Data Index: 557466 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1959010 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1444282 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1782268 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1334550 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1164217 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3455. Min Act: -0.0000

Data Index: 233577 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1989389 (The Pile)

Max Activating Token Index: 52