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

Dataset: The Pile

Neuron 2821 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: 0.6453. Min Range: -0.6453

Max Act: 0.6453. Min Act: -0.0000

Data Index: 226467 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6007. Min Act: -0.0000

Data Index: 231038 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5777. Min Act: -0.0000

Data Index: 422127 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6438. Min Act: -0.0000

Data Index: 466608 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6043. Min Act: -0.0000

Data Index: 826620 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.6288. Min Act: -0.0000

Data Index: 956442 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5632. Min Act: -0.0000

Data Index: 188778 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1966436 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5759. Min Act: -0.0000

Data Index: 455879 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5559. Min Act: -0.0000

Data Index: 665557 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1644202 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1295886 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1811045 (The Pile)

Max Activating Token Index: 75

Text #13

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5717. Min Act: -0.0000

Data Index: 741404 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1564751 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5737. Min Act: -0.0000

Data Index: 96723 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5326. Min Act: -0.0000

Data Index: 158844 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5221. Min Act: -0.0000

Data Index: 784384 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1420617 (The Pile)

Max Activating Token Index: 975

Text #19

Max Range: 0.6453. Min Range: -0.6453

Max Act: 0.5430. Min Act: -0.0000

Data Index: 602210 (The Pile)

Max Activating Token Index: 93