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

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

Neuron 3690 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.3234. Min Act: -0.0000

Data Index: 56644 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2865. Min Act: -0.0000

Data Index: 953691 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2788. Min Act: -0.0000

Data Index: 12453 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2778. Min Act: -0.0000

Data Index: 355035 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2743. Min Act: 0.0001

Data Index: 955422 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2921. Min Act: -0.0000

Data Index: 749950 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2597. Min Act: -0.0000

Data Index: 306913 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2582. Min Act: 0.0000

Data Index: 957477 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2562. Min Act: -0.0000

Data Index: 690991 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2556. Min Act: -0.0000

Data Index: 58421 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2532. Min Act: -0.0000

Data Index: 294300 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2352. Min Act: -0.0000

Data Index: 789270 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2273. Min Act: -0.0000

Data Index: 926935 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2334. Min Act: -0.0000

Data Index: 302899 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1114415 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2225. Min Act: -0.0000

Data Index: 343225 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2169. Min Act: 0.0001

Data Index: 532922 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2186. Min Act: -0.0000

Data Index: 858990 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2249. Min Act: -0.0000

Data Index: 334373 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2121. Min Act: -0.0000

Data Index: 256524 (C4 (Web Text))

Max Activating Token Index: 597