Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2046 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1609232 (Python Code)

Max Activating Token Index: 129

Text #1

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1094556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0090. Min Act: -0.0006

Data Index: 762356 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0006

Data Index: 505183 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0089. Min Act: -0.0006

Data Index: 186290 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1039237 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1290716 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1349587 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0006

Data Index: 750280 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0087. Min Act: -0.0006

Data Index: 590759 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0087. Min Act: -0.0006

Data Index: 995310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1189264 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0084. Min Act: -0.0006

Data Index: 972794 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1015435 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0083. Min Act: -0.0006

Data Index: 347542 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1304474 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0082. Min Act: -0.0006

Data Index: 923669 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0083. Min Act: -0.0006

Data Index: 572088 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0085. Min Act: -0.0006

Data Index: 309517 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0083. Min Act: -0.0006

Data Index: 588708 (C4 (Web Text))

Max Activating Token Index: 519