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

Dataset: The Pile

Neuron 1690 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0645. Min Act: -0.0000

Data Index: 889703 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0308. Min Act: -0.0000

Data Index: 1455411 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9105. Min Act: -0.0000

Data Index: 585271 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9082. Min Act: -0.0000

Data Index: 535517 (The Pile)

Max Activating Token Index: 43

Text #4

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7955. Min Act: -0.0000

Data Index: 429424 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7891. Min Act: -0.0000

Data Index: 278899 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1088138 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1492932 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7383. Min Act: -0.0000

Data Index: 331043 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1041437 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1925512 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6864. Min Act: -0.0000

Data Index: 417463 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6382. Min Act: -0.0000

Data Index: 605272 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7151. Min Act: -0.0000

Data Index: 785622 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7194. Min Act: -0.0000

Data Index: 196452 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6993. Min Act: -0.0000

Data Index: 277719 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6715. Min Act: -0.0000

Data Index: 875067 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6510. Min Act: -0.0000

Data Index: 929660 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1050391 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1318165 (The Pile)

Max Activating Token Index: 790