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

Dataset: The Pile

Neuron 570 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: 0.5688. Min Range: -0.5688

Max Act: 0.5637. Min Act: -0.0000

Data Index: 875200 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1064594 (The Pile)

Max Activating Token Index: 134

Text #2

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1757130 (The Pile)

Max Activating Token Index: 767

Text #3

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4485. Min Act: -0.0000

Data Index: 874518 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1033191 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4896. Min Act: -0.0000

Data Index: 805853 (The Pile)

Max Activating Token Index: 312

Text #6

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4443. Min Act: -0.0000

Data Index: 395005 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4728. Min Act: -0.0000

Data Index: 296880 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4905. Min Act: -0.0000

Data Index: 429457 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4516. Min Act: -0.0000

Data Index: 584538 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1649447 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1072857 (The Pile)

Max Activating Token Index: 272

Text #12

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1543431 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1145382 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4992. Min Act: -0.0000

Data Index: 870981 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1369323 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1146899 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4330. Min Act: -0.0000

Data Index: 188457 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3997. Min Act: -0.0000

Data Index: 752399 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3650. Min Act: -0.0000

Data Index: 404452 (The Pile)

Max Activating Token Index: 540