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

Dataset: The Pile

Neuron 1132 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: 1.8152. Min Range: -1.8152

Max Act: 1.8152. Min Act: -0.0000

Data Index: 955680 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.7462. Min Act: -0.0000

Data Index: 1121192 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5515. Min Act: -0.0000

Data Index: 788716 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.3096. Min Act: -0.0000

Data Index: 1770968 (The Pile)

Max Activating Token Index: 167

Text #4

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6628. Min Act: -0.0000

Data Index: 561699 (The Pile)

Max Activating Token Index: 715

Text #5

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5156. Min Act: -0.0000

Data Index: 1349866 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4497. Min Act: -0.0000

Data Index: 1011442 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6796. Min Act: -0.0000

Data Index: 1106872 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5589. Min Act: -0.0000

Data Index: 1140753 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1282925 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5854. Min Act: -0.0000

Data Index: 1669236 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.7254. Min Act: -0.0000

Data Index: 1951385 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5524. Min Act: -0.0000

Data Index: 100781 (The Pile)

Max Activating Token Index: 410

Text #13

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5455. Min Act: -0.0000

Data Index: 629434 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6436. Min Act: -0.0000

Data Index: 1334719 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6272. Min Act: 0.0000

Data Index: 60415 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5504. Min Act: -0.0000

Data Index: 1755221 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6318. Min Act: -0.0000

Data Index: 910265 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4481. Min Act: -0.0000

Data Index: 1655882 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5160. Min Act: -0.0000

Data Index: 458021 (The Pile)

Max Activating Token Index: 582