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

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

Neuron 4544 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3309. Min Act: -0.0000

Data Index: 269224 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2753. Min Act: -0.0000

Data Index: 974563 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2890. Min Act: -0.0000

Data Index: 568966 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2568. Min Act: 0.0000

Data Index: 743930 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2669. Min Act: 0.0000

Data Index: 1309267 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2399. Min Act: -0.0000

Data Index: 859339 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2413. Min Act: -0.0000

Data Index: 612487 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2416. Min Act: 0.0000

Data Index: 956141 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2400. Min Act: -0.0000

Data Index: 402004 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2325. Min Act: -0.0000

Data Index: 419569 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2234. Min Act: -0.0000

Data Index: 852134 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2085. Min Act: -0.0000

Data Index: 332689 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2069. Min Act: -0.0000

Data Index: 68314 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1113960 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.1830. Min Act: -0.0000

Data Index: 186736 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2043. Min Act: 0.0000

Data Index: 856664 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.1966. Min Act: -0.0000

Data Index: 303235 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.1939. Min Act: -0.0000

Data Index: 698173 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.1916. Min Act: -0.0000

Data Index: 991725 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.1823. Min Act: -0.0000

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 125