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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 711 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.4082. Min Act: -0.0001

Data Index: 908532 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.3679. Min Act: -0.0001

Data Index: 810075 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.4194. Min Act: -0.0001

Data Index: 372416 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2682. Min Act: -0.0001

Data Index: 994729 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2455. Min Act: -0.0001

Data Index: 1182004 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.1694. Min Act: -0.0001

Data Index: 109963 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.1428. Min Act: -0.0001

Data Index: 464069 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0973. Min Act: -0.0001

Data Index: 941165 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9864. Min Act: -0.0001

Data Index: 468389 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0464. Min Act: -0.0001

Data Index: 683952 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0377. Min Act: -0.0001

Data Index: 475023 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0396. Min Act: -0.0001

Data Index: 116272 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0329. Min Act: -0.0001

Data Index: 451200 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0603. Min Act: -0.0001

Data Index: 439788 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0276. Min Act: -0.0001

Data Index: 344337 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0805. Min Act: -0.0001

Data Index: 1190351 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0168. Min Act: -0.0001

Data Index: 97443 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.1128. Min Act: -0.0001

Data Index: 550252 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0372. Min Act: -0.0001

Data Index: 630294 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0303. Min Act: -0.0001

Data Index: 806693 (C4 (Web Text))

Max Activating Token Index: 349