Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1070 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0077. Min Act: -0.0003

Data Index: 945375 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0076. Min Act: -0.0003

Data Index: 252628 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0075. Min Act: -0.0003

Data Index: 900268 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0073. Min Act: -0.0003

Data Index: 74840 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0073. Min Act: -0.0003

Data Index: 237226 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0003

Data Index: 762189 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0003

Data Index: 33526 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1265728 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1006487 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0003

Data Index: 139419 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0003

Data Index: 428534 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0003

Data Index: 266735 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0003

Data Index: 835816 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1155314 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0003

Data Index: 771331 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0002

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0003

Data Index: 650100 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0003

Data Index: 858032 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1346191 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0064. Min Act: -0.0003

Data Index: 356046 (C4 (Web Text))

Max Activating Token Index: 807