Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 135 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0003

Data Index: 14733 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0115. Min Act: -0.0004

Data Index: 585009 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0111. Min Act: -0.0003

Data Index: 127179 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0004

Data Index: 658421 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1218184 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0109. Min Act: -0.0004

Data Index: 1186553 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1377455 (Python Code)

Max Activating Token Index: 92

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0004

Data Index: 565853 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0004

Data Index: 264784 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0004

Data Index: 843847 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0100. Min Act: -0.0004

Data Index: 411758 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0003

Data Index: 834510 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0100. Min Act: -0.0004

Data Index: 204011 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0097. Min Act: -0.0003

Data Index: 249292 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0097. Min Act: -0.0003

Data Index: 536692 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0099. Min Act: -0.0003

Data Index: 713457 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0098. Min Act: -0.0003

Data Index: 7444 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0088. Min Act: -0.0004

Data Index: 394632 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0096. Min Act: -0.0004

Data Index: 836968 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0093. Min Act: -0.0004

Data Index: 480683 (C4 (Web Text))

Max Activating Token Index: 669