Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5198 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.4185. Min Act: -0.0000

Data Index: 231976 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.3240. Min Act: -0.0000

Data Index: 402547 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2744. Min Act: -0.0000

Data Index: 144084 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1054314 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2932. Min Act: -0.0000

Data Index: 249280 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1032954 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2483. Min Act: -0.0000

Data Index: 744399 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1298706 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2703. Min Act: -0.0000

Data Index: 625613 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1304770 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2474. Min Act: -0.0000

Data Index: 642700 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1207059 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2765. Min Act: -0.0000

Data Index: 275229 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2767. Min Act: -0.0000

Data Index: 791107 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1041788 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2630. Min Act: -0.0000

Data Index: 818914 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1307568 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1227532 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2536. Min Act: -0.0000

Data Index: 791574 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1014008 (C4 (Web Text))

Max Activating Token Index: 12