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

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

Neuron 3089 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0123. Min Act: -0.0003

Data Index: 126953 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1002637 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0068. Min Act: -0.0003

Data Index: 492762 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1158133 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1308197 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1330716 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0094. Min Act: -0.0003

Data Index: 25646 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0079. Min Act: -0.0003

Data Index: 884928 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0077. Min Act: -0.0003

Data Index: 162305 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0086. Min Act: -0.0003

Data Index: 697196 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0083. Min Act: -0.0003

Data Index: 443339 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0075. Min Act: -0.0003

Data Index: 519875 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0075. Min Act: -0.0003

Data Index: 999952 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1067535 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0078. Min Act: -0.0003

Data Index: 9020 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1118949 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0080. Min Act: -0.0003

Data Index: 351678 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0073. Min Act: -0.0004

Data Index: 381445 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1150626 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1109325 (C4 (Web Text))

Max Activating Token Index: 770