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

Dataset: The Pile

Neuron 1445 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5337. Min Act: -0.0000

Data Index: 174339 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5848. Min Act: -0.0000

Data Index: 718137 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1993777 (The Pile)

Max Activating Token Index: 340

Text #3

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1116175 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5221. Min Act: -0.0000

Data Index: 763311 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5436. Min Act: -0.0000

Data Index: 813082 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1415817 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1622550 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3913. Min Act: -0.0000

Data Index: 108226 (The Pile)

Max Activating Token Index: 670

Text #9

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1884526 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4081. Min Act: -0.0000

Data Index: 741341 (The Pile)

Max Activating Token Index: 85

Text #11

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1529612 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1732741 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1064107 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1353944 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1330921 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4667. Min Act: -0.0000

Data Index: 892048 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1030582 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1063686 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1625433 (The Pile)

Max Activating Token Index: 145