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

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

Neuron 2474 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.3363. Min Act: 0.0000

Data Index: 270037 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.3116. Min Act: 0.0000

Data Index: 921435 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.1879. Min Act: -0.0000

Data Index: 841643 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.2473. Min Act: 0.0000

Data Index: 189136 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.1672. Min Act: -0.0000

Data Index: 854750 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.0809. Min Act: -0.0000

Data Index: 1229744 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.0700. Min Act: 0.0000

Data Index: 762249 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.0523. Min Act: 0.0000

Data Index: 774786 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1193744 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.0240. Min Act: 0.0000

Data Index: 1119591 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 1.3363. Min Range: -1.3363

Max Act: 1.0297. Min Act: -0.0000

Data Index: 445852 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9673. Min Act: -0.0000

Data Index: 341709 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9454. Min Act: -0.0000

Data Index: 742378 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9466. Min Act: -0.0000

Data Index: 546200 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.8991. Min Act: -0.0000

Data Index: 189306 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.7548. Min Act: 0.0000

Data Index: 965050 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.8774. Min Act: 0.0000

Data Index: 725480 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1098472 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.8906. Min Act: 0.0000

Data Index: 1276206 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.3363. Min Range: -1.3363

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1295902 (C4 (Web Text))

Max Activating Token Index: 982