Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1679 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0419. Min Act: -0.0006

Data Index: 902731 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0367. Min Act: -0.0006

Data Index: 1351264 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0351. Min Act: -0.0006

Data Index: 768302 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0347. Min Act: -0.0006

Data Index: 986062 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0342. Min Act: -0.0006

Data Index: 339395 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0320. Min Act: -0.0006

Data Index: 760500 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0331. Min Act: -0.0006

Data Index: 851232 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0331. Min Act: -0.0005

Data Index: 88635 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1324706 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0321. Min Act: -0.0006

Data Index: 907750 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0322. Min Act: -0.0006

Data Index: 883338 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1308853 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0329. Min Act: -0.0006

Data Index: 45723 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0315. Min Act: -0.0005

Data Index: 570788 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0308. Min Act: -0.0006

Data Index: 329946 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0320. Min Act: -0.0006

Data Index: 162931 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0321. Min Act: -0.0006

Data Index: 782207 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0318. Min Act: -0.0006

Data Index: 316962 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0317. Min Act: -0.0006

Data Index: 522018 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0317. Min Act: -0.0006

Data Index: 817180 (C4 (Web Text))

Max Activating Token Index: 63