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

Dataset: The Pile

Neuron 712 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: 0.5000. Min Range: -0.5000

Max Act: 0.5000. Min Act: -0.0000

Data Index: 570450 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1631384 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4829. Min Act: -0.0000

Data Index: 654295 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4447. Min Act: -0.0000

Data Index: 42502 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1251520 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4174. Min Act: -0.0000

Data Index: 924924 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1722690 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4094. Min Act: -0.0000

Data Index: 950376 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4153. Min Act: -0.0000

Data Index: 576983 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1563761 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3747. Min Act: -0.0000

Data Index: 567959 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3775. Min Act: -0.0000

Data Index: 10230 (The Pile)

Max Activating Token Index: 307

Text #12

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1669630 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3558. Min Act: -0.0000

Data Index: 212732 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1318195 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1955714 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3473. Min Act: -0.0000

Data Index: 878416 (The Pile)

Max Activating Token Index: 586

Text #17

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3111. Min Act: -0.0000

Data Index: 8447 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1331777 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1504968 (The Pile)

Max Activating Token Index: 996