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

Dataset: The Pile

Neuron 3792 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.5335. Min Act: -0.0001

Data Index: 1233595 (The Pile)

Max Activating Token Index: 695

Text #1

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4514. Min Act: -0.0001

Data Index: 424896 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4144. Min Act: -0.0001

Data Index: 1727051 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3926. Min Act: -0.0001

Data Index: 750669 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3998. Min Act: -0.0001

Data Index: 812515 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4091. Min Act: -0.0001

Data Index: 1940465 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4108. Min Act: -0.0001

Data Index: 182502 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4020. Min Act: -0.0001

Data Index: 132282 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3893. Min Act: -0.0001

Data Index: 906272 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1564216 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3693. Min Act: -0.0001

Data Index: 1840649 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3460. Min Act: -0.0001

Data Index: 1710886 (The Pile)

Max Activating Token Index: 31

Text #12

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3662. Min Act: -0.0001

Data Index: 1112387 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3548. Min Act: -0.0001

Data Index: 518125 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3664. Min Act: -0.0001

Data Index: 1151392 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3747. Min Act: -0.0001

Data Index: 406315 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3781. Min Act: -0.0001

Data Index: 145954 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3740. Min Act: -0.0001

Data Index: 1365635 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3693. Min Act: -0.0001

Data Index: 116394 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1191664 (The Pile)

Max Activating Token Index: 21