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

Dataset: The Pile

Neuron 4744 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1347162 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1837491 (The Pile)

Max Activating Token Index: 177

Text #2

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8539. Min Act: -0.0000

Data Index: 194733 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1555453 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8399. Min Act: -0.0000

Data Index: 746725 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7956. Min Act: -0.0000

Data Index: 433038 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1469527 (The Pile)

Max Activating Token Index: 589

Text #7

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7061. Min Act: -0.0000

Data Index: 590428 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1166147 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1848235 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1709150 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7538. Min Act: -0.0000

Data Index: 467351 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1102281 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1901467 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7539. Min Act: -0.0000

Data Index: 489868 (The Pile)

Max Activating Token Index: 874

Text #15

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1510734 (The Pile)

Max Activating Token Index: 550

Text #16

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7675. Min Act: -0.0000

Data Index: 200257 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1797780 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6935. Min Act: -0.0000

Data Index: 54733 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1576446 (The Pile)

Max Activating Token Index: 531