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

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

Neuron 2614 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.6138. Min Act: -0.0000

Data Index: 813852 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5617. Min Act: -0.0000

Data Index: 623769 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5633. Min Act: -0.0000

Data Index: 751758 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5102. Min Act: -0.0000

Data Index: 936542 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4797. Min Act: -0.0000

Data Index: 819920 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4544. Min Act: -0.0000

Data Index: 403071 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4984. Min Act: -0.0000

Data Index: 986248 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4156. Min Act: -0.0000

Data Index: 572447 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1223097 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4597. Min Act: -0.0000

Data Index: 144191 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4254. Min Act: -0.0000

Data Index: 209161 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4396. Min Act: -0.0000

Data Index: 227779 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4167. Min Act: -0.0000

Data Index: 411979 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4043. Min Act: -0.0000

Data Index: 323414 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4314. Min Act: -0.0000

Data Index: 779005 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3999. Min Act: -0.0000

Data Index: 333530 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4250. Min Act: -0.0000

Data Index: 541215 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3651. Min Act: -0.0000

Data Index: 95242 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3973. Min Act: -0.0000

Data Index: 599023 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3562. Min Act: -0.0000

Data Index: 704333 (C4 (Web Text))

Max Activating Token Index: 669