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

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

Neuron 3409 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0114. Min Act: -0.0002

Data Index: 321272 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0112. Min Act: -0.0002

Data Index: 304227 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1444174 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1328768 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0108. Min Act: -0.0002

Data Index: 1019998 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0108. Min Act: -0.0002

Data Index: 277197 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1009456 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0107. Min Act: -0.0002

Data Index: 428498 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1509640 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0106. Min Act: -0.0002

Data Index: 450233 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0106. Min Act: -0.0002

Data Index: 736741 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0105. Min Act: -0.0002

Data Index: 439638 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0103. Min Act: -0.0002

Data Index: 443266 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1207550 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1207464 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0105. Min Act: -0.0002

Data Index: 369384 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1189697 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1151769 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1121076 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1195309 (C4 (Web Text))

Max Activating Token Index: 881