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

Dataset: The Pile

Neuron 1149 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: 0.4039. Min Range: -0.4039

Max Act: 0.4039. Min Act: -0.0000

Data Index: 967043 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3407. Min Act: -0.0000

Data Index: 869213 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3528. Min Act: -0.0000

Data Index: 353615 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3643. Min Act: -0.0000

Data Index: 302636 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1519288 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1545141 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1092355 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1621348 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3381. Min Act: -0.0000

Data Index: 336107 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3349. Min Act: -0.0000

Data Index: 796902 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1801871 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1015769 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3385. Min Act: -0.0000

Data Index: 801360 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1467457 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3483. Min Act: -0.0000

Data Index: 77570 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3309. Min Act: -0.0000

Data Index: 456947 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3316. Min Act: -0.0000

Data Index: 483101 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1241777 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1728468 (The Pile)

Max Activating Token Index: 68

Text #19

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3285. Min Act: -0.0000

Data Index: 674209 (The Pile)

Max Activating Token Index: 241