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

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

Neuron 4765 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1490927 (Python Code)

Max Activating Token Index: 38

Text #1

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0225. Min Act: -0.0000

Data Index: 1117026 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0225. Min Act: -0.0000

Data Index: 566491 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0227. Min Act: -0.0000

Data Index: 247687 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0223. Min Act: -0.0000

Data Index: 363271 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0222. Min Act: -0.0000

Data Index: 1201359 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0212. Min Act: -0.0000

Data Index: 1122686 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0201. Min Act: -0.0000

Data Index: 992946 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0198. Min Act: -0.0000

Data Index: 741272 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0207. Min Act: -0.0000

Data Index: 960486 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0202. Min Act: -0.0000

Data Index: 165272 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0201. Min Act: -0.0000

Data Index: 1448943 (Python Code)

Max Activating Token Index: 476

Text #12

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0200. Min Act: -0.0000

Data Index: 786235 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0197. Min Act: -0.0000

Data Index: 1304527 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0190. Min Act: -0.0000

Data Index: 1443353 (Python Code)

Max Activating Token Index: 155

Text #15

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0188. Min Act: -0.0000

Data Index: 1512588 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0182. Min Act: -0.0000

Data Index: 113964 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0195. Min Act: -0.0000

Data Index: 1101662 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0193. Min Act: -0.0000

Data Index: 940308 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0199. Min Act: -0.0000

Data Index: 54995 (C4 (Web Text))

Max Activating Token Index: 238