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

Dataset: The Pile

Neuron 585 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9175. Min Range: -5.9175

Max Act: 5.8025. Min Act: -0.0000

Data Index: 1738178 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 5.9175. Min Range: -5.9175

Max Act: 5.9175. Min Act: -0.0000

Data Index: 66203 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 5.9175. Min Range: -5.9175

Max Act: 5.9151. Min Act: -0.0000

Data Index: 34376 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 5.9175. Min Range: -5.9175

Max Act: 5.0944. Min Act: -0.0000

Data Index: 1827814 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 5.9175. Min Range: -5.9175

Max Act: 5.2440. Min Act: -0.0000

Data Index: 1279043 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.7447. Min Act: -0.0000

Data Index: 199864 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 5.9175. Min Range: -5.9175

Max Act: 5.0272. Min Act: -0.0000

Data Index: 69333 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 5.9175. Min Range: -5.9175

Max Act: 5.0054. Min Act: -0.0000

Data Index: 1435540 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.6133. Min Act: -0.0000

Data Index: 1782791 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.6332. Min Act: -0.0000

Data Index: 1512297 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.9746. Min Act: -0.0000

Data Index: 393892 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.5617. Min Act: -0.0000

Data Index: 1519467 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.6061. Min Act: -0.0000

Data Index: 1027755 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.6858. Min Act: -0.0000

Data Index: 471627 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.5225. Min Act: -0.0000

Data Index: 218010 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.6872. Min Act: -0.0000

Data Index: 702883 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.7331. Min Act: -0.0000

Data Index: 1659772 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.8579. Min Act: -0.0000

Data Index: 1618339 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.8424. Min Act: -0.0000

Data Index: 1204277 (The Pile)

Max Activating Token Index: 914

Text #19

Max Range: 5.9175. Min Range: -5.9175

Max Act: 4.8133. Min Act: -0.0000

Data Index: 1037078 (The Pile)

Max Activating Token Index: 724