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

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

Neuron 4989 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1328467 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7237. Min Act: -0.0000

Data Index: 131628 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7418. Min Act: -0.0000

Data Index: 150091 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7334. Min Act: -0.0000

Data Index: 85665 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7274. Min Act: -0.0000

Data Index: 367160 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1009983 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7009. Min Act: -0.0000

Data Index: 280544 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1213682 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1079525 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1253667 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7073. Min Act: -0.0000

Data Index: 60594 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.6657. Min Act: -0.0000

Data Index: 415132 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.7024. Min Act: -0.0000

Data Index: 27422 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1025338 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.6732. Min Act: -0.0000

Data Index: 261621 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.6458. Min Act: -0.0000

Data Index: 877068 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.6688. Min Act: -0.0000

Data Index: 831400 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.6435. Min Act: -0.0000

Data Index: 57701 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.5970. Min Act: -0.0000

Data Index: 543641 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.6314. Min Act: -0.0000

Data Index: 981829 (C4 (Web Text))

Max Activating Token Index: 643