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

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

Neuron 4003 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.8079. Min Act: -0.0000

Data Index: 540584 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.5153. Min Act: -0.0000

Data Index: 171071 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4380. Min Act: -0.0000

Data Index: 4847 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4441. Min Act: -0.0000

Data Index: 703674 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3088. Min Act: -0.0000

Data Index: 18088 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.4369. Min Act: -0.0000

Data Index: 1057015 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2713. Min Act: -0.0001

Data Index: 1629000 (Python Code)

Max Activating Token Index: 960

Text #7

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.3535. Min Act: -0.0000

Data Index: 163705 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1355869 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2041. Min Act: -0.0000

Data Index: 755892 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2090. Min Act: -0.0001

Data Index: 1474357 (Python Code)

Max Activating Token Index: 991

Text #11

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.2217. Min Act: -0.0000

Data Index: 1235965 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1333003 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.1955. Min Act: -0.0000

Data Index: 849318 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.0601. Min Act: -0.0000

Data Index: 302729 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1603182 (Python Code)

Max Activating Token Index: 824

Text #16

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1424051 (Python Code)

Max Activating Token Index: 876

Text #17

Max Range: 1.8079. Min Range: -1.8079

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1386477 (Python Code)

Max Activating Token Index: 981

Text #18

Max Range: 1.8079. Min Range: -1.8079

Max Act: 1.0407. Min Act: -0.0000

Data Index: 104231 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.8079. Min Range: -1.8079

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1027124 (C4 (Web Text))

Max Activating Token Index: 751