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

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

Neuron 1056 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1626209 (Python Code)

Max Activating Token Index: 699

Text #1

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0101. Min Act: -0.0003

Data Index: 286175 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0096. Min Act: -0.0003

Data Index: 960097 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0094. Min Act: -0.0003

Data Index: 216991 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0094. Min Act: -0.0002

Data Index: 831022 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1647033 (Python Code)

Max Activating Token Index: 160

Text #6

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0003

Data Index: 715912 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0003

Data Index: 903139 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0003

Data Index: 614684 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0003

Data Index: 151682 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0003

Data Index: 42599 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0091. Min Act: -0.0003

Data Index: 208918 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0091. Min Act: -0.0003

Data Index: 368186 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1284478 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1498053 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0088. Min Act: -0.0003

Data Index: 757207 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1020100 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1196981 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0088. Min Act: -0.0003

Data Index: 52783 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0088. Min Act: -0.0003

Data Index: 44862 (C4 (Web Text))

Max Activating Token Index: 731