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

Dataset: The Pile

Neuron 4026 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0452. Min Range: -1.0452

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1348527 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 1.0452. Min Range: -1.0452

Max Act: 1.0452. Min Act: -0.0000

Data Index: 400250 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1735071 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.9542. Min Act: -0.0000

Data Index: 511939 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.9537. Min Act: -0.0000

Data Index: 332955 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1960819 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.9285. Min Act: -0.0000

Data Index: 842779 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1932287 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8134. Min Act: -0.0000

Data Index: 674690 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8619. Min Act: -0.0000

Data Index: 735415 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7924. Min Act: -0.0000

Data Index: 19404 (The Pile)

Max Activating Token Index: 28

Text #11

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.8295. Min Act: -0.0000

Data Index: 337601 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1929311 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1893820 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1216248 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1636737 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1466548 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7940. Min Act: -0.0000

Data Index: 925908 (The Pile)

Max Activating Token Index: 796

Text #18

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1258330 (The Pile)

Max Activating Token Index: 979

Text #19

Max Range: 1.0452. Min Range: -1.0452

Max Act: 0.7389. Min Act: -0.0000

Data Index: 547551 (The Pile)

Max Activating Token Index: 289