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

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

Neuron 1029 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: 0.0720. Min Range: -0.0720

Max Act: 0.0720. Min Act: -0.0002

Data Index: 450880 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1315379 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0577. Min Act: -0.0002

Data Index: 96153 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1358322 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0608. Min Act: -0.0002

Data Index: 155863 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1345588 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0632. Min Act: -0.0002

Data Index: 810713 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0587. Min Act: -0.0002

Data Index: 429009 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0572. Min Act: -0.0002

Data Index: 709172 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1297695 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0531. Min Act: -0.0002

Data Index: 596494 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0554. Min Act: -0.0002

Data Index: 243455 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1163680 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0548. Min Act: -0.0002

Data Index: 678343 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0577. Min Act: -0.0002

Data Index: 623861 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0543. Min Act: -0.0002

Data Index: 563064 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0568. Min Act: -0.0002

Data Index: 781107 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0518. Min Act: -0.0002

Data Index: 929252 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0600. Min Act: -0.0002

Data Index: 521220 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1117057 (C4 (Web Text))

Max Activating Token Index: 113