Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1870 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1496074 (Python Code)

Max Activating Token Index: 204

Text #1

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1369713 (Python Code)

Max Activating Token Index: 462

Text #2

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0249. Min Act: -0.0001

Data Index: 84846 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1411557 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1475138 (Python Code)

Max Activating Token Index: 219

Text #5

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0241. Min Act: -0.0001

Data Index: 367145 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1393615 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1250765 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1506718 (Python Code)

Max Activating Token Index: 979

Text #9

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1550491 (Python Code)

Max Activating Token Index: 726

Text #10

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1400179 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1512234 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1628172 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1144847 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1539178 (Python Code)

Max Activating Token Index: 557

Text #15

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1079181 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0227. Min Act: -0.0001

Data Index: 337617 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0214. Min Act: -0.0001

Data Index: 188224 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1220149 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1580508 (Python Code)

Max Activating Token Index: 351