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

Dataset: The Pile

Neuron 2036 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0652. Min Range: -1.0652

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1535662 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1476191 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8265. Min Act: -0.0000

Data Index: 781722 (The Pile)

Max Activating Token Index: 448

Text #3

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1808015 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1995163 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7454. Min Act: -0.0000

Data Index: 930091 (The Pile)

Max Activating Token Index: 858

Text #6

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1428597 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7005. Min Act: -0.0000

Data Index: 355387 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.6033. Min Act: -0.0000

Data Index: 721157 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1709326 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7353. Min Act: -0.0000

Data Index: 27603 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1043812 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7113. Min Act: -0.0000

Data Index: 411994 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7147. Min Act: 0.0000

Data Index: 382154 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1238243 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.6930. Min Act: -0.0000

Data Index: 274087 (The Pile)

Max Activating Token Index: 446

Text #16

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1991802 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7099. Min Act: -0.0000

Data Index: 974197 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1590362 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.6551. Min Act: -0.0000

Data Index: 785862 (The Pile)

Max Activating Token Index: 279