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

Dataset: The Pile

Neuron 416 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: 0.9567. Min Range: -0.9567

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1100354 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1281987 (The Pile)

Max Activating Token Index: 844

Text #2

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1436615 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8996. Min Act: -0.0000

Data Index: 323827 (The Pile)

Max Activating Token Index: 534

Text #4

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7970. Min Act: -0.0000

Data Index: 420630 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7341. Min Act: -0.0000

Data Index: 378196 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7600. Min Act: 0.0000

Data Index: 1664251 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1779053 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1080366 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1659456 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7269. Min Act: -0.0000

Data Index: 478368 (The Pile)

Max Activating Token Index: 126

Text #11

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1276635 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1982510 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7597. Min Act: -0.0000

Data Index: 685282 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6648. Min Act: -0.0000

Data Index: 908146 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1566113 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6770. Min Act: -0.0000

Data Index: 988331 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6948. Min Act: -0.0000

Data Index: 334970 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6723. Min Act: -0.0000

Data Index: 207103 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6428. Min Act: -0.0000

Data Index: 155581 (The Pile)

Max Activating Token Index: 467