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

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

Neuron 356 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.6247. Min Act: -0.0002

Data Index: 850064 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5843. Min Act: -0.0002

Data Index: 347132 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5656. Min Act: -0.0002

Data Index: 1083019 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5475. Min Act: -0.0002

Data Index: 996417 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5451. Min Act: -0.0002

Data Index: 937281 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5454. Min Act: -0.0003

Data Index: 1152512 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5334. Min Act: -0.0002

Data Index: 351568 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5321. Min Act: -0.0002

Data Index: 650273 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5192. Min Act: -0.0003

Data Index: 198426 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5007. Min Act: -0.0002

Data Index: 1286030 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5177. Min Act: -0.0002

Data Index: 477974 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5153. Min Act: -0.0002

Data Index: 711556 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5147. Min Act: -0.0002

Data Index: 706128 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5164. Min Act: -0.0002

Data Index: 175498 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4897. Min Act: -0.0002

Data Index: 383736 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5077. Min Act: -0.0003

Data Index: 676278 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5215. Min Act: -0.0002

Data Index: 851602 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4940. Min Act: -0.0003

Data Index: 337034 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4841. Min Act: -0.0002

Data Index: 981300 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5000. Min Act: -0.0002

Data Index: 277323 (C4 (Web Text))

Max Activating Token Index: 391