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

Dataset: The Pile

Neuron 3938 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3646. Min Act: -0.0000

Data Index: 870044 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0973. Min Act: -0.0000

Data Index: 138885 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1824612 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1076592 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1043142 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9372. Min Act: -0.0000

Data Index: 627623 (The Pile)

Max Activating Token Index: 172

Text #6

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8849. Min Act: -0.0000

Data Index: 116614 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9800. Min Act: -0.0000

Data Index: 116486 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8448. Min Act: -0.0000

Data Index: 704169 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1681834 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8867. Min Act: -0.0000

Data Index: 642040 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1495036 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8122. Min Act: 0.0000

Data Index: 1430282 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1608796 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1661887 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8404. Min Act: -0.0000

Data Index: 305052 (The Pile)

Max Activating Token Index: 452

Text #16

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1614151 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.7869. Min Act: 0.0000

Data Index: 1495066 (The Pile)

Max Activating Token Index: 931

Text #18

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8063. Min Act: 0.0000

Data Index: 1301295 (The Pile)

Max Activating Token Index: 196

Text #19

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.8406. Min Act: -0.0000

Data Index: 6146 (The Pile)

Max Activating Token Index: 290