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

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

Neuron 4608 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2601. Min Act: -0.0002

Data Index: 722677 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2166. Min Act: -0.0002

Data Index: 999369 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2089. Min Act: -0.0002

Data Index: 624018 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2015. Min Act: -0.0002

Data Index: 506648 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2043. Min Act: -0.0002

Data Index: 467260 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1935. Min Act: -0.0002

Data Index: 703245 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1758. Min Act: -0.0002

Data Index: 1125024 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1908. Min Act: -0.0002

Data Index: 371380 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1936. Min Act: -0.0002

Data Index: 280788 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1726. Min Act: -0.0002

Data Index: 1200323 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1613. Min Act: -0.0002

Data Index: 702651 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1688. Min Act: -0.0002

Data Index: 1290045 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1788. Min Act: -0.0002

Data Index: 831808 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1864. Min Act: -0.0002

Data Index: 899279 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1729. Min Act: -0.0002

Data Index: 649044 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1714. Min Act: -0.0002

Data Index: 1179377 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1732. Min Act: -0.0002

Data Index: 794790 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1694. Min Act: -0.0002

Data Index: 94826 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1629. Min Act: -0.0002

Data Index: 605107 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1668. Min Act: -0.0002

Data Index: 529401 (C4 (Web Text))

Max Activating Token Index: 313