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

Dataset: The Pile

Neuron 4506 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: 1.1605. Min Range: -1.1605

Max Act: 1.1605. Min Act: -0.0000

Data Index: 481277 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1487506 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0163. Min Act: -0.0000

Data Index: 225080 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0295. Min Act: -0.0000

Data Index: 339329 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9494. Min Act: -0.0000

Data Index: 37600 (The Pile)

Max Activating Token Index: 401

Text #5

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1961926 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1382140 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.8914. Min Act: -0.0000

Data Index: 385551 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9682. Min Act: -0.0000

Data Index: 809696 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0134. Min Act: -0.0000

Data Index: 387589 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 1.1605. Min Range: -1.1605

Max Act: 1.0163. Min Act: -0.0000

Data Index: 273827 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1581335 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9908. Min Act: -0.0000

Data Index: 915094 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.8844. Min Act: -0.0000

Data Index: 999723 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1681868 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1740296 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9240. Min Act: -0.0000

Data Index: 999283 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1887847 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1272621 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 1.1605. Min Range: -1.1605

Max Act: 0.8013. Min Act: -0.0000

Data Index: 334005 (The Pile)

Max Activating Token Index: 902