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

Dataset: The Pile

Neuron 885 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1093960 (The Pile)

Max Activating Token Index: 367

Text #1

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1690831 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1436895 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3259. Min Act: -0.0000

Data Index: 356224 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1570115 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3501. Min Act: -0.0000

Data Index: 434164 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1951529 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1505005 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3249. Min Act: -0.0000

Data Index: 558387 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2873. Min Act: -0.0000

Data Index: 320486 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1063465 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2799. Min Act: -0.0000

Data Index: 10107 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2709. Min Act: -0.0000

Data Index: 694136 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1528966 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2750. Min Act: -0.0000

Data Index: 717588 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1066643 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1038689 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2635. Min Act: -0.0000

Data Index: 40874 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1981502 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1409352 (The Pile)

Max Activating Token Index: 268