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

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

Neuron 1897 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: 0.0080. Min Range: -0.0080

Max Act: 0.0080. Min Act: -0.0005

Data Index: 57760 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0054. Min Act: -0.0004

Data Index: 1333966 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0054. Min Act: -0.0005

Data Index: 367846 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0052. Min Act: -0.0004

Data Index: 1420160 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0052. Min Act: -0.0004

Data Index: 1317887 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1367905 (Python Code)

Max Activating Token Index: 583

Text #6

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0049. Min Act: -0.0004

Data Index: 398642 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1388406 (Python Code)

Max Activating Token Index: 978

Text #8

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0050. Min Act: -0.0004

Data Index: 700185 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0049. Min Act: -0.0005

Data Index: 461051 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0048. Min Act: -0.0005

Data Index: 607413 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0049. Min Act: -0.0004

Data Index: 1171793 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0049. Min Act: -0.0005

Data Index: 830927 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0050. Min Act: -0.0005

Data Index: 817250 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0049. Min Act: -0.0005

Data Index: 650035 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0050. Min Act: -0.0005

Data Index: 753140 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0049. Min Act: -0.0004

Data Index: 103035 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0048. Min Act: -0.0004

Data Index: 1200945 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0049. Min Act: -0.0004

Data Index: 795190 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0049. Min Act: -0.0005

Data Index: 404317 (C4 (Web Text))

Max Activating Token Index: 735