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

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

Neuron 3581 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3210. Min Act: -0.0000

Data Index: 335312 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3213. Min Act: -0.0000

Data Index: 53782 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3367. Min Act: -0.0000

Data Index: 960687 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1057579 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1280554 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3410. Min Act: -0.0000

Data Index: 766824 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1060094 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1246480 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3357. Min Act: -0.0000

Data Index: 687659 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3000. Min Act: -0.0000

Data Index: 687171 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1271597 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1119705 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1171950 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1091754 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1096931 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3063. Min Act: -0.0000

Data Index: 355908 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2968. Min Act: -0.0000

Data Index: 164475 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3147. Min Act: -0.0000

Data Index: 308614 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.3041. Min Act: -0.0000

Data Index: 959127 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.3410. Min Range: -0.3410

Max Act: 0.2985. Min Act: -0.0000

Data Index: 775619 (C4 (Web Text))

Max Activating Token Index: 199