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

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

Neuron 986 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: 0.0114. Min Range: -0.0114

Max Act: 0.0114. Min Act: -0.0006

Data Index: 504805 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0092. Min Act: -0.0006

Data Index: 807414 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0089. Min Act: -0.0006

Data Index: 904225 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0088. Min Act: -0.0006

Data Index: 41112 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0006

Data Index: 337446 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0085. Min Act: -0.0006

Data Index: 648354 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0083. Min Act: -0.0005

Data Index: 435529 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0085. Min Act: -0.0006

Data Index: 258555 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1019840 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0084. Min Act: -0.0005

Data Index: 446516 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0082. Min Act: -0.0006

Data Index: 910236 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1220738 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1275728 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0082. Min Act: -0.0006

Data Index: 946148 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1189034 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1278274 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0080. Min Act: -0.0005

Data Index: 924741 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0078. Min Act: -0.0006

Data Index: 1062262 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0078. Min Act: -0.0006

Data Index: 49429 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0076. Min Act: -0.0006

Data Index: 184214 (C4 (Web Text))

Max Activating Token Index: 314