Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2654 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1234440 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1561897 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1577207 (Python Code)

Max Activating Token Index: 932

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1580556 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0219. Min Act: -0.0003

Data Index: 266270 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0220. Min Act: -0.0003

Data Index: 493279 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0206. Min Act: -0.0004

Data Index: 849326 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0204. Min Act: -0.0003

Data Index: 749477 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1263720 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0200. Min Act: -0.0003

Data Index: 677149 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0199. Min Act: -0.0004

Data Index: 1214258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0196. Min Act: -0.0003

Data Index: 348693 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0196. Min Act: -0.0003

Data Index: 251134 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1560669 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0193. Min Act: -0.0003

Data Index: 390899 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0193. Min Act: -0.0004

Data Index: 915947 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0193. Min Act: -0.0003

Data Index: 582295 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0189. Min Act: -0.0003

Data Index: 60138 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0196. Min Act: -0.0003

Data Index: 46947 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0191. Min Act: -0.0003

Data Index: 57605 (C4 (Web Text))

Max Activating Token Index: 447