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

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

Neuron 786 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9631. Min Act: -0.0002

Data Index: 258296 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9716. Min Act: -0.0001

Data Index: 1037339 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9661. Min Act: -0.0001

Data Index: 919105 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8647. Min Act: -0.0001

Data Index: 913531 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8015. Min Act: -0.0001

Data Index: 914916 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8861. Min Act: -0.0001

Data Index: 1332206 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8842. Min Act: -0.0001

Data Index: 1089387 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8455. Min Act: -0.0001

Data Index: 1241442 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8355. Min Act: -0.0001

Data Index: 779684 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8017. Min Act: -0.0001

Data Index: 598856 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8419. Min Act: -0.0001

Data Index: 399479 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8184. Min Act: -0.0001

Data Index: 861226 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7946. Min Act: -0.0001

Data Index: 88705 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8164. Min Act: -0.0001

Data Index: 661418 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7463. Min Act: -0.0001

Data Index: 129078 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7739. Min Act: -0.0001

Data Index: 351446 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.6939. Min Act: -0.0001

Data Index: 876658 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8394. Min Act: -0.0001

Data Index: 411551 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8063. Min Act: -0.0001

Data Index: 205117 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7496. Min Act: -0.0001

Data Index: 945721 (C4 (Web Text))

Max Activating Token Index: 622