Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2818 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6769. Min Act: -0.0003

Data Index: 1199309 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.7576. Min Act: -0.0003

Data Index: 1144944 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6669. Min Act: -0.0003

Data Index: 942599 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6879. Min Act: -0.0003

Data Index: 60947 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6582. Min Act: -0.0003

Data Index: 1242537 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6981. Min Act: -0.0003

Data Index: 276136 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6755. Min Act: -0.0004

Data Index: 1225685 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6755. Min Act: -0.0003

Data Index: 807825 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6755. Min Act: -0.0003

Data Index: 1162177 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6791. Min Act: -0.0003

Data Index: 1065046 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6103. Min Act: -0.0003

Data Index: 173099 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6276. Min Act: -0.0003

Data Index: 642382 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6871. Min Act: -0.0003

Data Index: 467528 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6266. Min Act: -0.0003

Data Index: 626082 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5971. Min Act: -0.0003

Data Index: 410826 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6954. Min Act: -0.0003

Data Index: 394140 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6747. Min Act: -0.0003

Data Index: 847436 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6755. Min Act: -0.0003

Data Index: 769531 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6516. Min Act: -0.0003

Data Index: 739559 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.6120. Min Act: -0.0003

Data Index: 670585 (C4 (Web Text))

Max Activating Token Index: 719