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

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

Neuron 5461 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: 0.7655. Min Range: -0.7655

Max Act: 0.7401. Min Act: -0.0000

Data Index: 289799 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6964. Min Act: -0.0000

Data Index: 893558 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7655. Min Act: -0.0000

Data Index: 357177 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6588. Min Act: -0.0000

Data Index: 646829 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6447. Min Act: -0.0000

Data Index: 432223 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6153. Min Act: -0.0000

Data Index: 225257 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1229822 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6389. Min Act: -0.0000

Data Index: 33507 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1125052 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6697. Min Act: -0.0000

Data Index: 359905 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5922. Min Act: -0.0000

Data Index: 382579 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5427. Min Act: -0.0000

Data Index: 411641 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5966. Min Act: -0.0000

Data Index: 313264 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5386. Min Act: -0.0000

Data Index: 672554 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1336925 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5908. Min Act: -0.0000

Data Index: 559203 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5372. Min Act: -0.0000

Data Index: 440906 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5677. Min Act: -0.0000

Data Index: 368181 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5128. Min Act: -0.0000

Data Index: 633474 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.4979. Min Act: -0.0000

Data Index: 401474 (C4 (Web Text))

Max Activating Token Index: 269