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

Dataset: The Pile

Neuron 3839 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.6806. Min Act: -0.0000

Data Index: 569808 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.8106. Min Act: -0.0000

Data Index: 99674 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7755. Min Act: -0.0000

Data Index: 376689 (The Pile)

Max Activating Token Index: 719

Text #3

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7490. Min Act: -0.0000

Data Index: 121352 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1985306 (The Pile)

Max Activating Token Index: 367

Text #5

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1361831 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1007218 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7284. Min Act: -0.0000

Data Index: 736614 (The Pile)

Max Activating Token Index: 410

Text #8

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7173. Min Act: -0.0000

Data Index: 43699 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1277339 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1135526 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7038. Min Act: -0.0000

Data Index: 280757 (The Pile)

Max Activating Token Index: 877

Text #12

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1298797 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7344. Min Act: -0.0000

Data Index: 311 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1609572 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1013007 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1678726 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1553850 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.6956. Min Act: -0.0000

Data Index: 161360 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.6726. Min Act: -0.0000

Data Index: 362972 (The Pile)

Max Activating Token Index: 464