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

Dataset: The Pile

Neuron 3702 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0254. Min Act: -0.0000

Data Index: 162496 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1973369 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1001749 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1882433 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9736. Min Act: -0.0000

Data Index: 923457 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0395. Min Act: -0.0000

Data Index: 377977 (The Pile)

Max Activating Token Index: 763

Text #6

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1964400 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0235. Min Act: -0.0000

Data Index: 1296824 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9878. Min Act: -0.0000

Data Index: 300387 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1048191 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1501883 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9656. Min Act: -0.0000

Data Index: 855874 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1668354 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0150. Min Act: -0.0000

Data Index: 479782 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1996964 (The Pile)

Max Activating Token Index: 319

Text #15

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9366. Min Act: -0.0000

Data Index: 548856 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1130411 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1923922 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1643067 (The Pile)

Max Activating Token Index: 437

Text #19

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9527. Min Act: -0.0000

Data Index: 386327 (The Pile)

Max Activating Token Index: 686