Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2212 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1321192 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.5279. Min Act: -0.0000

Data Index: 558587 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1226449 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1516196 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1854231 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1334921 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.5001. Min Act: -0.0000

Data Index: 392095 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1937036 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4966. Min Act: -0.0000

Data Index: 292856 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.5078. Min Act: -0.0000

Data Index: 798683 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4852. Min Act: -0.0000

Data Index: 785045 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1187217 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1591502 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1658954 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4554. Min Act: -0.0000

Data Index: 584491 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1612053 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4471. Min Act: -0.0000

Data Index: 280828 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4523. Min Act: -0.0000

Data Index: 340546 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1060053 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4587. Min Act: -0.0000

Data Index: 903402 (The Pile)

Max Activating Token Index: 750