Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 302 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0003

Data Index: 487704 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0111. Min Act: -0.0003

Data Index: 450384 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0110. Min Act: -0.0003

Data Index: 498277 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0111. Min Act: -0.0003

Data Index: 914234 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1572783 (Python Code)

Max Activating Token Index: 608

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1076898 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1628850 (Python Code)

Max Activating Token Index: 233

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1562364 (Python Code)

Max Activating Token Index: 891

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0106. Min Act: -0.0003

Data Index: 89063 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1629795 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1516804 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1133903 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1025788 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0096. Min Act: -0.0003

Data Index: 361447 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1221225 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0096. Min Act: -0.0003

Data Index: 789227 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0098. Min Act: -0.0003

Data Index: 96671 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1439622 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1093691 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0091. Min Act: -0.0003

Data Index: 27492 (C4 (Web Text))

Max Activating Token Index: 885