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

Dataset: The Pile

Neuron 3703 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.8106. Min Act: -0.0000

Data Index: 298823 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.8488. Min Act: -0.0000

Data Index: 965237 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1108486 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7617. Min Act: -0.0000

Data Index: 389076 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7547. Min Act: -0.0000

Data Index: 633261 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7328. Min Act: -0.0000

Data Index: 782716 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1616200 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1774182 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6963. Min Act: -0.0000

Data Index: 797937 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6575. Min Act: -0.0000

Data Index: 933374 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1678447 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1190367 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.5272. Min Act: -0.0000

Data Index: 955241 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6933. Min Act: -0.0000

Data Index: 943992 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1671541 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6530. Min Act: -0.0000

Data Index: 32889 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1411311 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6599. Min Act: -0.0000

Data Index: 649900 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6209. Min Act: -0.0000

Data Index: 557089 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1449238 (The Pile)

Max Activating Token Index: 396