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

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

Neuron 3545 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.8249. Min Act: -0.0000

Data Index: 481751 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.9262. Min Act: -0.0000

Data Index: 900859 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.8575. Min Act: -0.0000

Data Index: 449726 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.8347. Min Act: -0.0000

Data Index: 155750 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.7677. Min Act: -0.0000

Data Index: 620529 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.7714. Min Act: -0.0000

Data Index: 23223 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.7357. Min Act: -0.0000

Data Index: 909942 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.7122. Min Act: -0.0000

Data Index: 953639 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.7071. Min Act: -0.0000

Data Index: 659342 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.8019. Min Act: -0.0000

Data Index: 280334 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.6512. Min Act: -0.0000

Data Index: 1198107 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.4491. Min Act: -0.0000

Data Index: 30624 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.6180. Min Act: -0.0000

Data Index: 833711 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.5734. Min Act: -0.0000

Data Index: 763727 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.5694. Min Act: -0.0000

Data Index: 743712 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.5633. Min Act: -0.0000

Data Index: 1170483 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.5315. Min Act: -0.0000

Data Index: 118364 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.4180. Min Act: -0.0000

Data Index: 55982 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.5371. Min Act: -0.0000

Data Index: 961287 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 2.9262. Min Range: -2.9262

Max Act: 2.5207. Min Act: -0.0000

Data Index: 790336 (C4 (Web Text))

Max Activating Token Index: 955