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

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

Neuron 1832 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1253879 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1014731 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1715 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7085. Min Act: -0.0000

Data Index: 928985 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7366. Min Act: -0.0000

Data Index: 399961 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6814. Min Act: -0.0000

Data Index: 245871 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6737. Min Act: -0.0000

Data Index: 123009 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6407. Min Act: -0.0000

Data Index: 568751 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6730. Min Act: -0.0000

Data Index: 911846 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6941. Min Act: -0.0000

Data Index: 52849 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1028845 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7101. Min Act: -0.0000

Data Index: 909380 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6591. Min Act: -0.0000

Data Index: 503583 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6673. Min Act: -0.0000

Data Index: 849002 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1343007 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1260452 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7051. Min Act: -0.0000

Data Index: 739496 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7020. Min Act: -0.0000

Data Index: 301935 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7120. Min Act: -0.0000

Data Index: 313348 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6344. Min Act: -0.0000

Data Index: 657357 (C4 (Web Text))

Max Activating Token Index: 591