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

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

Neuron 2756 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: 0.0375. Min Range: -0.0375

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1156674 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1262262 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0002

Data Index: 270094 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0328. Min Act: -0.0002

Data Index: 673571 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0351. Min Act: -0.0002

Data Index: 910093 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0270. Min Act: -0.0002

Data Index: 993025 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0300. Min Act: -0.0002

Data Index: 500524 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0313. Min Act: -0.0002

Data Index: 961758 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0292. Min Act: -0.0002

Data Index: 213158 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0298. Min Act: -0.0002

Data Index: 577410 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0297. Min Act: -0.0002

Data Index: 354567 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0318. Min Act: -0.0002

Data Index: 674934 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1235143 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0300. Min Act: -0.0002

Data Index: 300487 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1503726 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1563984 (Python Code)

Max Activating Token Index: 893

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1629834 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0292. Min Act: -0.0002

Data Index: 294464 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1139118 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0321. Min Act: -0.0002

Data Index: 285822 (C4 (Web Text))

Max Activating Token Index: 308