Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4127 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2519. Min Act: -0.0001

Data Index: 839870 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2629. Min Act: -0.0001

Data Index: 491379 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1196131 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2232. Min Act: -0.0001

Data Index: 901201 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1958. Min Act: -0.0001

Data Index: 1239316 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2023. Min Act: -0.0001

Data Index: 800478 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2069. Min Act: -0.0001

Data Index: 688900 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2271. Min Act: -0.0001

Data Index: 730455 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2186. Min Act: -0.0001

Data Index: 327759 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2029. Min Act: -0.0001

Data Index: 1140374 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1952. Min Act: -0.0001

Data Index: 127879 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2118. Min Act: -0.0001

Data Index: 228085 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1961. Min Act: -0.0001

Data Index: 1032398 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1999. Min Act: -0.0001

Data Index: 880101 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1081786 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2007. Min Act: -0.0001

Data Index: 18921 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1124799 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.1995. Min Act: -0.0001

Data Index: 25968 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2073. Min Act: -0.0002

Data Index: 562464 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.2629. Min Range: -0.2629

Max Act: 0.2001. Min Act: -0.0001

Data Index: 872061 (C4 (Web Text))

Max Activating Token Index: 62