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

Dataset: The Pile

Neuron 3003 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: 1.4842. Min Range: -1.4842

Max Act: 1.4842. Min Act: -0.0000

Data Index: 1012388 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2949. Min Act: -0.0000

Data Index: 179277 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2346. Min Act: -0.0000

Data Index: 666450 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1348. Min Act: -0.0000

Data Index: 696750 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2564. Min Act: -0.0000

Data Index: 558079 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1142038 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2018. Min Act: -0.0000

Data Index: 966352 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1884997 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.0571. Min Act: -0.0000

Data Index: 850484 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1179. Min Act: -0.0000

Data Index: 836727 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1838. Min Act: -0.0000

Data Index: 382225 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1580411 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1472. Min Act: -0.0000

Data Index: 1709084 (The Pile)

Max Activating Token Index: 194

Text #13

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1704102 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1758. Min Act: -0.0000

Data Index: 978695 (The Pile)

Max Activating Token Index: 520

Text #15

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.0925. Min Act: -0.0000

Data Index: 890974 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1168. Min Act: -0.0000

Data Index: 494450 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1671. Min Act: -0.0000

Data Index: 88125 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1160314 (The Pile)

Max Activating Token Index: 767

Text #19

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.0774. Min Act: -0.0000

Data Index: 1473401 (The Pile)

Max Activating Token Index: 887