Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3424 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1121982 (The Pile)

Max Activating Token Index: 225

Text #1

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1874982 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1370626 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9417. Min Act: -0.0000

Data Index: 933240 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9639. Min Act: -0.0000

Data Index: 845065 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9137. Min Act: -0.0000

Data Index: 309968 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1335757 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.8773. Min Act: -0.0000

Data Index: 637864 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.8320. Min Act: -0.0000

Data Index: 215833 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.8258. Min Act: -0.0000

Data Index: 413187 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7644. Min Act: -0.0000

Data Index: 323166 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1857207 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.8018. Min Act: -0.0000

Data Index: 968695 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1137964 (The Pile)

Max Activating Token Index: 70

Text #14

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7597. Min Act: -0.0000

Data Index: 250989 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7677. Min Act: -0.0000

Data Index: 280518 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1572247 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1797491 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7408. Min Act: -0.0000

Data Index: 399122 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1960270 (The Pile)

Max Activating Token Index: 51