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

Dataset: The Pile

Neuron 4474 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.3685. Min Act: 0.0000

Data Index: 1323492 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1637704 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.2663. Min Act: -0.0000

Data Index: 459754 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.1361. Min Act: -0.0000

Data Index: 61544 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.2026. Min Act: -0.0000

Data Index: 461903 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.1560. Min Act: -0.0000

Data Index: 70439 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1601681 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.0711. Min Act: -0.0000

Data Index: 988411 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1907445 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.0524. Min Act: -0.0000

Data Index: 981395 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.1133. Min Act: -0.0000

Data Index: 679370 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1187538 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1170621 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9135. Min Act: -0.0000

Data Index: 51789 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1096342 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.8408. Min Act: -0.0000

Data Index: 917747 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1938685 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1155869 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1251395 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.8491. Min Act: -0.0000

Data Index: 556541 (The Pile)

Max Activating Token Index: 727