Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1022 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.5240. Min Act: -0.0002

Data Index: 825152 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.5116. Min Act: -0.0002

Data Index: 609146 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.5297. Min Act: -0.0002

Data Index: 110033 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.4223. Min Act: -0.0002

Data Index: 720280 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3742. Min Act: -0.0002

Data Index: 1050548 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.4199. Min Act: -0.0002

Data Index: 391502 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.4017. Min Act: -0.0002

Data Index: 818848 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3991. Min Act: -0.0002

Data Index: 875998 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3403. Min Act: -0.0002

Data Index: 1116670 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3589. Min Act: -0.0002

Data Index: 781007 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3397. Min Act: -0.0002

Data Index: 278875 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3212. Min Act: -0.0002

Data Index: 459445 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3615. Min Act: -0.0002

Data Index: 369474 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3722. Min Act: -0.0002

Data Index: 1319926 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3651. Min Act: -0.0002

Data Index: 707712 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.2998. Min Act: -0.0002

Data Index: 966 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.2875. Min Act: -0.0002

Data Index: 565304 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.3044. Min Act: -0.0002

Data Index: 357916 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.2282. Min Act: -0.0002

Data Index: 99608 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 2.5297. Min Range: -2.5297

Max Act: 2.2760. Min Act: -0.0002

Data Index: 674541 (C4 (Web Text))

Max Activating Token Index: 512