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

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

Neuron 731 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: 1.3061. Min Range: -1.3061

Max Act: 1.2904. Min Act: -0.0000

Data Index: 348122 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.3061. Min Act: -0.0000

Data Index: 762794 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1383. Min Act: -0.0000

Data Index: 62069 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2030. Min Act: -0.0000

Data Index: 441669 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2063. Min Act: -0.0000

Data Index: 717111 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1229963 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1951. Min Act: -0.0000

Data Index: 134903 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0988. Min Act: -0.0000

Data Index: 599497 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0760. Min Act: -0.0000

Data Index: 59953 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1255396 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2026. Min Act: -0.0000

Data Index: 925279 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0501. Min Act: -0.0000

Data Index: 791048 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1040. Min Act: -0.0000

Data Index: 886665 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0287. Min Act: -0.0000

Data Index: 680680 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1693. Min Act: -0.0000

Data Index: 9186 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0983. Min Act: -0.0000

Data Index: 831263 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0931. Min Act: -0.0000

Data Index: 953993 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0969. Min Act: -0.0000

Data Index: 390656 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0354. Min Act: -0.0000

Data Index: 265651 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0311. Min Act: -0.0000

Data Index: 77224 (C4 (Web Text))

Max Activating Token Index: 833