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

Dataset: The Pile

Neuron 3990 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.2166. Min Act: -0.0000

Data Index: 710933 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0824. Min Act: -0.0000

Data Index: 185358 (The Pile)

Max Activating Token Index: 154

Text #2

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8533. Min Act: -0.0000

Data Index: 159938 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1220139 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1701409 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1660132 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1498893 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7653. Min Act: -0.0000

Data Index: 917568 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1500855 (The Pile)

Max Activating Token Index: 774

Text #9

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8178. Min Act: -0.0000

Data Index: 186821 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7147. Min Act: -0.0000

Data Index: 526820 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7408. Min Act: -0.0000

Data Index: 282401 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7041. Min Act: -0.0000

Data Index: 672638 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6550. Min Act: -0.0000

Data Index: 527815 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1895684 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7182. Min Act: -0.0000

Data Index: 111066 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6631. Min Act: -0.0000

Data Index: 575387 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1156451 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1969530 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1686433 (The Pile)

Max Activating Token Index: 592