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

Dataset: The Pile

Neuron 2858 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: 3.6114. Min Range: -3.6114

Max Act: 3.6114. Min Act: -0.0000

Data Index: 1761701 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 3.6114. Min Range: -3.6114

Max Act: 3.0717. Min Act: -0.0000

Data Index: 239808 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 3.6114. Min Range: -3.6114

Max Act: 3.1905. Min Act: -0.0000

Data Index: 984128 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 3.6114. Min Range: -3.6114

Max Act: 3.1018. Min Act: -0.0000

Data Index: 421999 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.8277. Min Act: -0.0000

Data Index: 1566513 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.9414. Min Act: -0.0000

Data Index: 319764 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.8173. Min Act: -0.0000

Data Index: 1772846 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.8139. Min Act: -0.0000

Data Index: 455967 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.7772. Min Act: -0.0000

Data Index: 1448835 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.6434. Min Act: -0.0000

Data Index: 566041 (The Pile)

Max Activating Token Index: 806

Text #10

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.7075. Min Act: -0.0000

Data Index: 1944781 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.4870. Min Act: -0.0000

Data Index: 1517468 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.7757. Min Act: -0.0000

Data Index: 727001 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.6043. Min Act: -0.0000

Data Index: 890901 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.6139. Min Act: -0.0000

Data Index: 131506 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.2337. Min Act: -0.0000

Data Index: 938506 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.5442. Min Act: -0.0000

Data Index: 995069 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.5554. Min Act: -0.0000

Data Index: 963310 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.7978. Min Act: -0.0000

Data Index: 596603 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 3.6114. Min Range: -3.6114

Max Act: 2.3844. Min Act: -0.0000

Data Index: 538834 (The Pile)

Max Activating Token Index: 94