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

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

Neuron 5636 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1376. Min Act: -0.0002

Data Index: 613265 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1304. Min Act: -0.0002

Data Index: 689205 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1295928 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1019. Min Act: -0.0002

Data Index: 399939 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1054. Min Act: -0.0002

Data Index: 159953 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0996. Min Act: -0.0002

Data Index: 232920 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1007. Min Act: -0.0002

Data Index: 103994 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1082043 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1029. Min Act: -0.0002

Data Index: 69853 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1024. Min Act: -0.0002

Data Index: 532439 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1536269 (Python Code)

Max Activating Token Index: 346

Text #11

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0994. Min Act: -0.0002

Data Index: 1617441 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1504554 (Python Code)

Max Activating Token Index: 669

Text #13

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1630727 (Python Code)

Max Activating Token Index: 275

Text #14

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1434653 (Python Code)

Max Activating Token Index: 880

Text #15

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1244145 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1399725 (Python Code)

Max Activating Token Index: 575

Text #17

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0943. Min Act: -0.0002

Data Index: 216876 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1533088 (Python Code)

Max Activating Token Index: 763

Text #19

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1055298 (C4 (Web Text))

Max Activating Token Index: 853