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

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

Neuron 2735 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2408. Min Act: -0.0001

Data Index: 244019 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2857. Min Act: -0.0001

Data Index: 1352722 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2725. Min Act: -0.0001

Data Index: 554126 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2604. Min Act: -0.0001

Data Index: 337724 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2311. Min Act: -0.0001

Data Index: 175915 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2369. Min Act: -0.0001

Data Index: 116557 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2069. Min Act: -0.0001

Data Index: 527378 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1713. Min Act: -0.0001

Data Index: 1357488 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1721. Min Act: -0.0001

Data Index: 1063050 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1642. Min Act: -0.0001

Data Index: 1176268 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1029. Min Act: -0.0001

Data Index: 792708 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1937. Min Act: -0.0001

Data Index: 532877 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1672. Min Act: -0.0001

Data Index: 1134927 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1277. Min Act: -0.0001

Data Index: 457819 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2215. Min Act: -0.0001

Data Index: 1224894 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2838. Min Act: -0.0001

Data Index: 98957 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1124. Min Act: -0.0001

Data Index: 679191 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1799. Min Act: -0.0001

Data Index: 627817 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1328. Min Act: -0.0001

Data Index: 847223 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.1188. Min Act: -0.0001

Data Index: 820036 (C4 (Web Text))

Max Activating Token Index: 345