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

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

Neuron 5060 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: 2.1245. Min Range: -2.1245

Max Act: 2.1245. Min Act: -0.0000

Data Index: 369219 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 2.1245. Min Range: -2.1245

Max Act: 2.1179. Min Act: -0.0000

Data Index: 1229754 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.9928. Min Act: -0.0000

Data Index: 82579 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 2.1245. Min Range: -2.1245

Max Act: 2.0221. Min Act: -0.0000

Data Index: 202472 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.8042. Min Act: -0.0000

Data Index: 151465 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.8908. Min Act: -0.0000

Data Index: 1063394 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.9130. Min Act: -0.0000

Data Index: 399152 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.7617. Min Act: -0.0000

Data Index: 901503 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.7813. Min Act: -0.0000

Data Index: 867228 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.6403. Min Act: -0.0000

Data Index: 979732 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.7160. Min Act: -0.0000

Data Index: 273355 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.7006. Min Act: -0.0000

Data Index: 1216153 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.6358. Min Act: -0.0000

Data Index: 1260939 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.6332. Min Act: -0.0000

Data Index: 1220147 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.5291. Min Act: -0.0000

Data Index: 121964 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.5438. Min Act: -0.0000

Data Index: 167510 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.6150. Min Act: -0.0000

Data Index: 465939 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.6298. Min Act: -0.0000

Data Index: 683306 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.5336. Min Act: -0.0000

Data Index: 823241 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 2.1245. Min Range: -2.1245

Max Act: 1.6099. Min Act: -0.0000

Data Index: 373895 (C4 (Web Text))

Max Activating Token Index: 817