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

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

Neuron 1637 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0142. Min Range: -1.0142

Max Act: 1.0142. Min Act: -0.0001

Data Index: 94913 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.9987. Min Act: -0.0002

Data Index: 1130131 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.9269. Min Act: -0.0002

Data Index: 70467 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.9718. Min Act: -0.0002

Data Index: 1295263 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.9884. Min Act: -0.0001

Data Index: 1278681 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 1.0142. Min Range: -1.0142

Max Act: 1.0089. Min Act: -0.0002

Data Index: 735903 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.9773. Min Act: -0.0002

Data Index: 328559 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8890. Min Act: -0.0002

Data Index: 814442 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8550. Min Act: -0.0001

Data Index: 851733 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.9313. Min Act: -0.0002

Data Index: 242934 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8755. Min Act: -0.0002

Data Index: 90431 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8602. Min Act: -0.0002

Data Index: 782416 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8524. Min Act: -0.0002

Data Index: 966756 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7800. Min Act: -0.0002

Data Index: 458866 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8279. Min Act: -0.0002

Data Index: 558440 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8867. Min Act: -0.0002

Data Index: 207558 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8549. Min Act: -0.0002

Data Index: 1356857 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8461. Min Act: -0.0001

Data Index: 632447 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7929. Min Act: -0.0001

Data Index: 657130 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7921. Min Act: -0.0001

Data Index: 493152 (C4 (Web Text))

Max Activating Token Index: 265