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

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

Neuron 777 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1114. Min Range: -4.1114

Max Act: 4.0720. Min Act: -0.0000

Data Index: 525662 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.9761. Min Act: -0.0000

Data Index: 410566 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 4.1114. Min Range: -4.1114

Max Act: 4.1114. Min Act: -0.0000

Data Index: 532841 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.8364. Min Act: -0.0000

Data Index: 359657 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 4.1114. Min Range: -4.1114

Max Act: 4.0668. Min Act: -0.0000

Data Index: 134978 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.8939. Min Act: -0.0000

Data Index: 806222 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.9995. Min Act: -0.0000

Data Index: 1329035 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.8343. Min Act: -0.0000

Data Index: 544091 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.5984. Min Act: -0.0000

Data Index: 930642 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.7399. Min Act: -0.0000

Data Index: 453880 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.7573. Min Act: -0.0000

Data Index: 704941 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.7288. Min Act: -0.0000

Data Index: 1029474 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.6956. Min Act: -0.0000

Data Index: 397864 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.6538. Min Act: -0.0000

Data Index: 1117476 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.2587. Min Act: -0.0000

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.3825. Min Act: -0.0000

Data Index: 1086010 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.7091. Min Act: -0.0000

Data Index: 980460 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.5108. Min Act: -0.0000

Data Index: 964625 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 4.1114. Min Range: -4.1114

Max Act: 2.9302. Min Act: -0.0000

Data Index: 465623 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 4.1114. Min Range: -4.1114

Max Act: 3.4872. Min Act: -0.0000

Data Index: 21252 (C4 (Web Text))

Max Activating Token Index: 944