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

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

Neuron 1086 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: 812074 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0097. Min Act: -0.0006

Data Index: 164535 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0092. Min Act: -0.0006

Data Index: 806292 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1095291 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1085716 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1191701 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0091. Min Act: -0.0006

Data Index: 875606 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0088. Min Act: -0.0006

Data Index: 863683 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0088. Min Act: -0.0006

Data Index: 831150 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0088. Min Act: -0.0006

Data Index: 102005 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1302937 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0085. Min Act: -0.0006

Data Index: 572311 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1585245 (Python Code)

Max Activating Token Index: 686

Text #13

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0086. Min Act: -0.0006

Data Index: 429613 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1243229 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1238303 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1184484 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0084. Min Act: -0.0006

Data Index: 32439 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1339467 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1045578 (C4 (Web Text))

Max Activating Token Index: 529