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

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

Neuron 2637 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0196. Min Act: -0.0004

Data Index: 1017698 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1456919 (Python Code)

Max Activating Token Index: 251

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0214. Min Act: -0.0004

Data Index: 1398579 (Python Code)

Max Activating Token Index: 444

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0170. Min Act: -0.0004

Data Index: 535628 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0210. Min Act: -0.0004

Data Index: 1417672 (Python Code)

Max Activating Token Index: 758

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0207. Min Act: -0.0004

Data Index: 609363 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0212. Min Act: -0.0004

Data Index: 1593761 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0201. Min Act: -0.0004

Data Index: 163086 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0202. Min Act: -0.0004

Data Index: 889769 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0201. Min Act: -0.0004

Data Index: 1512257 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0182. Min Act: -0.0004

Data Index: 531111 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0185. Min Act: -0.0004

Data Index: 1269253 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0205. Min Act: -0.0004

Data Index: 1502260 (Python Code)

Max Activating Token Index: 685

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0189. Min Act: -0.0004

Data Index: 152042 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0200. Min Act: -0.0004

Data Index: 1553589 (Python Code)

Max Activating Token Index: 87

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0191. Min Act: -0.0004

Data Index: 1540672 (Python Code)

Max Activating Token Index: 875

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1383864 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0195. Min Act: -0.0004

Data Index: 1105123 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0197. Min Act: -0.0004

Data Index: 451253 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0189. Min Act: -0.0004

Data Index: 563645 (C4 (Web Text))

Max Activating Token Index: 418