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

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

Neuron 2372 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7692. Min Act: -0.0000

Data Index: 422495 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6598. Min Act: -0.0000

Data Index: 761316 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6417. Min Act: -0.0000

Data Index: 122692 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1243118 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1169643 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5377. Min Act: -0.0000

Data Index: 608244 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5447. Min Act: -0.0000

Data Index: 675819 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1070659 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1328387 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4964. Min Act: -0.0000

Data Index: 593166 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1155797 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4474. Min Act: -0.0000

Data Index: 356069 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1040370 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4713. Min Act: -0.0000

Data Index: 895904 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4659. Min Act: -0.0000

Data Index: 592989 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4884. Min Act: -0.0000

Data Index: 675045 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4794. Min Act: -0.0000

Data Index: 978695 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1359139 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4644. Min Act: -0.0000

Data Index: 618886 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4467. Min Act: -0.0000

Data Index: 856292 (C4 (Web Text))

Max Activating Token Index: 978