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

Dataset: The Pile

Neuron 656 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.1983. Min Act: -0.0000

Data Index: 834847 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.2179. Min Act: -0.0000

Data Index: 1027355 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1428814 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0872. Min Act: -0.0000

Data Index: 701948 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.1239. Min Act: -0.0000

Data Index: 1773231 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1169346 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0226. Min Act: -0.0000

Data Index: 697530 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.1450. Min Act: -0.0000

Data Index: 588392 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.1295. Min Act: -0.0000

Data Index: 460556 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1962448 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1995344 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1655220 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1463374 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9330. Min Act: -0.0000

Data Index: 941039 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9793. Min Act: -0.0000

Data Index: 164322 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1714603 (The Pile)

Max Activating Token Index: 446

Text #16

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9591. Min Act: -0.0000

Data Index: 100627 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9311. Min Act: -0.0000

Data Index: 332415 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8718. Min Act: -0.0000

Data Index: 35346 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1637028 (The Pile)

Max Activating Token Index: 906