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

Dataset: The Pile

Neuron 4284 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: 1.2257. Min Range: -1.2257

Max Act: 1.2257. Min Act: -0.0000

Data Index: 1138174 (The Pile)

Max Activating Token Index: 969

Text #1

Max Range: 1.2257. Min Range: -1.2257

Max Act: 1.0836. Min Act: -0.0000

Data Index: 1886450 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 1.2257. Min Range: -1.2257

Max Act: 1.0233. Min Act: -0.0000

Data Index: 1982752 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9914. Min Act: -0.0000

Data Index: 997735 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1373728 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9497. Min Act: -0.0000

Data Index: 995474 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9542. Min Act: -0.0000

Data Index: 723084 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9391. Min Act: -0.0000

Data Index: 158194 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1655511 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8638. Min Act: -0.0000

Data Index: 78852 (The Pile)

Max Activating Token Index: 740

Text #10

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8928. Min Act: -0.0000

Data Index: 18545 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8843. Min Act: -0.0000

Data Index: 714158 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8440. Min Act: -0.0000

Data Index: 94068 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8430. Min Act: -0.0000

Data Index: 216306 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8638. Min Act: -0.0000

Data Index: 125960 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1377427 (The Pile)

Max Activating Token Index: 624

Text #16

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1627330 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8168. Min Act: -0.0000

Data Index: 320040 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1122865 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 1.2257. Min Range: -1.2257

Max Act: 0.8268. Min Act: -0.0000

Data Index: 967336 (The Pile)

Max Activating Token Index: 714