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

Dataset: The Pile

Neuron 4206 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: 1.1599. Min Range: -1.1599

Max Act: 1.1599. Min Act: -0.0000

Data Index: 509726 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1213566 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9085. Min Act: -0.0000

Data Index: 687561 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9253. Min Act: -0.0000

Data Index: 441326 (The Pile)

Max Activating Token Index: 48

Text #4

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1135326 (The Pile)

Max Activating Token Index: 827

Text #5

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8524. Min Act: -0.0000

Data Index: 5351 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9058. Min Act: -0.0000

Data Index: 648962 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8975. Min Act: -0.0000

Data Index: 772747 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9246. Min Act: -0.0000

Data Index: 376550 (The Pile)

Max Activating Token Index: 453

Text #9

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1692250 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1161827 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8733. Min Act: -0.0000

Data Index: 119798 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8639. Min Act: -0.0000

Data Index: 673703 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8411. Min Act: -0.0000

Data Index: 758830 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1511389 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1576160 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1455163 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1508742 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8531. Min Act: -0.0000

Data Index: 64605 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.7853. Min Act: -0.0000

Data Index: 336000 (The Pile)

Max Activating Token Index: 624