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

Dataset: The Pile

Neuron 2923 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: 0.5586. Min Range: -0.5586

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1107019 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1860330 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1841338 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4145. Min Act: -0.0000

Data Index: 66695 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3722. Min Act: -0.0000

Data Index: 43031 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3974. Min Act: -0.0000

Data Index: 857675 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3901. Min Act: -0.0000

Data Index: 509485 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1622780 (The Pile)

Max Activating Token Index: 487

Text #8

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1031134 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1139974 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1686787 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1420955 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3584. Min Act: -0.0000

Data Index: 497200 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3538. Min Act: -0.0000

Data Index: 548934 (The Pile)

Max Activating Token Index: 865

Text #14

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1905489 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1145763 (The Pile)

Max Activating Token Index: 276

Text #16

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3216. Min Act: -0.0000

Data Index: 917640 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1302070 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1393676 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3247. Min Act: -0.0000

Data Index: 935953 (The Pile)

Max Activating Token Index: 264