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

Dataset: The Pile

Neuron 2671 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: 1.0067. Min Range: -1.0067

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1134079 (The Pile)

Max Activating Token Index: 409

Text #1

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9528. Min Act: -0.0000

Data Index: 270348 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9667. Min Act: -0.0000

Data Index: 355085 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8944. Min Act: -0.0000

Data Index: 315123 (The Pile)

Max Activating Token Index: 759

Text #4

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1363378 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9514. Min Act: -0.0000

Data Index: 74456 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9443. Min Act: -0.0000

Data Index: 403034 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.9228. Min Act: -0.0000

Data Index: 105435 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1950130 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8511. Min Act: -0.0000

Data Index: 582264 (The Pile)

Max Activating Token Index: 504

Text #10

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1355074 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8726. Min Act: -0.0000

Data Index: 657334 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1653343 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1012922 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1358436 (The Pile)

Max Activating Token Index: 98

Text #15

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1489658 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8730. Min Act: -0.0000

Data Index: 738009 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1639058 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.8049. Min Act: -0.0000

Data Index: 501225 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 1.0067. Min Range: -1.0067

Max Act: 0.7363. Min Act: -0.0000

Data Index: 609669 (The Pile)

Max Activating Token Index: 692