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

Dataset: The Pile

Neuron 2702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.7699. Min Act: -0.0000

Data Index: 342756 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.2695. Min Act: -0.0000

Data Index: 365798 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1969. Min Act: -0.0000

Data Index: 315130 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1623044 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1832791 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1932. Min Act: -0.0000

Data Index: 685677 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1138109 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1550. Min Act: -0.0000

Data Index: 952876 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1488. Min Act: -0.0000

Data Index: 583006 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1949. Min Act: -0.0000

Data Index: 872727 (The Pile)

Max Activating Token Index: 183

Text #10

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1121004 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1050. Min Act: -0.0000

Data Index: 280336 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1945464 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.0629. Min Act: -0.0000

Data Index: 1886128 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1390. Min Act: -0.0000

Data Index: 193050 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.0472. Min Act: -0.0000

Data Index: 260531 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1305683 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.0212. Min Act: -0.0000

Data Index: 103749 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.0936. Min Act: -0.0000

Data Index: 870221 (The Pile)

Max Activating Token Index: 667

Text #19

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.0148. Min Act: -0.0000

Data Index: 675098 (The Pile)

Max Activating Token Index: 182