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

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

Neuron 870 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.4231. Min Act: -0.0000

Data Index: 882192 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.3021. Min Act: -0.0001

Data Index: 649064 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.3040. Min Act: -0.0001

Data Index: 813077 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.3052. Min Act: -0.0001

Data Index: 215848 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.2067. Min Act: -0.0000

Data Index: 143019 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.2303. Min Act: -0.0000

Data Index: 916619 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1867. Min Act: -0.0000

Data Index: 623345 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.2157. Min Act: -0.0001

Data Index: 801316 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.2133. Min Act: -0.0001

Data Index: 1082625 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.2085. Min Act: -0.0000

Data Index: 323738 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1627. Min Act: -0.0000

Data Index: 186053 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1091824 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1855. Min Act: -0.0001

Data Index: 296359 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1685. Min Act: -0.0000

Data Index: 809766 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1737. Min Act: -0.0000

Data Index: 421024 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1290. Min Act: -0.0001

Data Index: 860652 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1569. Min Act: -0.0000

Data Index: 273674 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1970. Min Act: -0.0000

Data Index: 866253 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1197945 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.1336. Min Act: -0.0000

Data Index: 369196 (C4 (Web Text))

Max Activating Token Index: 771