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

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

Neuron 769 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.7193. Min Act: -0.0000

Data Index: 1322893 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.3572. Min Act: -0.0000

Data Index: 707669 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1016701 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.3135. Min Act: -0.0000

Data Index: 367298 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1165378 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.2899. Min Act: -0.0000

Data Index: 659744 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.3607. Min Act: -0.0000

Data Index: 1074102 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.2838. Min Act: -0.0000

Data Index: 970421 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1283740 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.3484. Min Act: -0.0000

Data Index: 1180852 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.2500. Min Act: -0.0000

Data Index: 1640947 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.2415. Min Act: 0.0000

Data Index: 568091 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.3502. Min Act: -0.0000

Data Index: 91883 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.2078. Min Act: -0.0000

Data Index: 557452 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.2817. Min Act: -0.0000

Data Index: 1236086 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.2346. Min Act: -0.0000

Data Index: 1407476 (Python Code)

Max Activating Token Index: 914

Text #16

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.1926. Min Act: -0.0000

Data Index: 534397 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.1543. Min Act: -0.0000

Data Index: 20060 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.2077. Min Act: -0.0000

Data Index: 978994 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.7193. Min Range: -1.7193

Max Act: 1.1795. Min Act: -0.0000

Data Index: 526894 (C4 (Web Text))

Max Activating Token Index: 412