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

Dataset: The Pile

Neuron 2860 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: 1.3791. Min Range: -1.3791

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1860305 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1141809 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.2258. Min Act: -0.0000

Data Index: 483977 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.2917. Min Act: -0.0000

Data Index: 745838 (The Pile)

Max Activating Token Index: 927

Text #4

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.2867. Min Act: -0.0000

Data Index: 628457 (The Pile)

Max Activating Token Index: 212

Text #5

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1734601 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0360. Min Act: -0.0000

Data Index: 880725 (The Pile)

Max Activating Token Index: 451

Text #7

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0669. Min Act: -0.0000

Data Index: 721057 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0542. Min Act: -0.0000

Data Index: 892247 (The Pile)

Max Activating Token Index: 95

Text #9

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0246. Min Act: -0.0000

Data Index: 1317574 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0524. Min Act: -0.0000

Data Index: 153013 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1042571 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0152. Min Act: -0.0000

Data Index: 105805 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1970898 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 1.3791. Min Range: -1.3791

Max Act: 0.9305. Min Act: -0.0000

Data Index: 281100 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0490. Min Act: -0.0000

Data Index: 339359 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 1.3791. Min Range: -1.3791

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1334068 (The Pile)

Max Activating Token Index: 711

Text #17

Max Range: 1.3791. Min Range: -1.3791

Max Act: 1.0287. Min Act: -0.0000

Data Index: 420626 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 1.3791. Min Range: -1.3791

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1532674 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 1.3791. Min Range: -1.3791

Max Act: 0.9534. Min Act: -0.0000

Data Index: 997800 (The Pile)

Max Activating Token Index: 102