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

Dataset: The Pile

Neuron 1505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.3457. Min Act: -0.0000

Data Index: 285627 (The Pile)

Max Activating Token Index: 586

Text #1

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.2248. Min Act: -0.0000

Data Index: 398888 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0921. Min Act: -0.0000

Data Index: 883467 (The Pile)

Max Activating Token Index: 200

Text #3

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1293982 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1871627 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9784. Min Act: -0.0000

Data Index: 841272 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0137. Min Act: -0.0000

Data Index: 302181 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1137280 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9222. Min Act: -0.0000

Data Index: 62813 (The Pile)

Max Activating Token Index: 922

Text #9

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.8529. Min Act: -0.0000

Data Index: 663890 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9089. Min Act: -0.0000

Data Index: 180667 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1304084 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.8881. Min Act: -0.0000

Data Index: 973283 (The Pile)

Max Activating Token Index: 312

Text #13

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.8402. Min Act: -0.0000

Data Index: 169790 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1141473 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.8648. Min Act: -0.0000

Data Index: 915387 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.8313. Min Act: -0.0000

Data Index: 406598 (The Pile)

Max Activating Token Index: 407

Text #17

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1984428 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1556721 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1700128 (The Pile)

Max Activating Token Index: 846