Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1344757 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.1510. Min Act: -0.0000

Data Index: 757077 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1610456 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.1833. Min Act: -0.0000

Data Index: 267583 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1361914 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.0311. Min Act: -0.0000

Data Index: 821274 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8915. Min Act: -0.0000

Data Index: 855386 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1073876 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1894072 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1647591 (The Pile)

Max Activating Token Index: 361

Text #10

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1506355 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 1.1833. Min Range: -1.1833

Max Act: 1.0462. Min Act: -0.0000

Data Index: 576993 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8978. Min Act: -0.0000

Data Index: 872827 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.7633. Min Act: -0.0000

Data Index: 296848 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9434. Min Act: -0.0000

Data Index: 651331 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1199610 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1036551 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1229292 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1392639 (The Pile)

Max Activating Token Index: 276

Text #19

Max Range: 1.1833. Min Range: -1.1833

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1907050 (The Pile)

Max Activating Token Index: 728