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

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

Neuron 1490 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: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1015800 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0090. Min Act: -0.0003

Data Index: 23673 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0090. Min Act: -0.0003

Data Index: 355272 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0090. Min Act: -0.0003

Data Index: 893284 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0089. Min Act: -0.0003

Data Index: 603920 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0088. Min Act: -0.0003

Data Index: 110162 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0089. Min Act: -0.0003

Data Index: 108094 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0088. Min Act: -0.0003

Data Index: 432865 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1200353 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0088. Min Act: -0.0003

Data Index: 143034 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0087. Min Act: -0.0003

Data Index: 825599 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1081843 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1217254 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0003

Data Index: 199332 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0003

Data Index: 120134 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1348944 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0085. Min Act: -0.0003

Data Index: 518262 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0085. Min Act: -0.0003

Data Index: 931619 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1099108 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1055632 (C4 (Web Text))

Max Activating Token Index: 41