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

Dataset: The Pile

Neuron 3659 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1370844 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1143011 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4337. Min Act: -0.0000

Data Index: 208872 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1507052 (The Pile)

Max Activating Token Index: 889

Text #4

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3912. Min Act: -0.0000

Data Index: 468257 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1748650 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3796. Min Act: -0.0000

Data Index: 933435 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3778. Min Act: -0.0000

Data Index: 976755 (The Pile)

Max Activating Token Index: 542

Text #8

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3755. Min Act: -0.0000

Data Index: 267030 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3382. Min Act: -0.0000

Data Index: 21980 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3615. Min Act: -0.0000

Data Index: 596240 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3784. Min Act: -0.0000

Data Index: 284120 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1714800 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3772. Min Act: -0.0000

Data Index: 264417 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3490. Min Act: -0.0000

Data Index: 320730 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1585998 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1609963 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1359015 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3429. Min Act: -0.0000

Data Index: 377768 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.2968. Min Act: -0.0000

Data Index: 943614 (The Pile)

Max Activating Token Index: 748