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

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

Neuron 1780 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1641. Min Act: -0.0001

Data Index: 778880 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1508. Min Act: -0.0001

Data Index: 379811 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1375. Min Act: -0.0001

Data Index: 419112 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1447. Min Act: -0.0001

Data Index: 716309 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1546. Min Act: -0.0001

Data Index: 1004411 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1254. Min Act: -0.0001

Data Index: 891098 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1344. Min Act: -0.0001

Data Index: 81911 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1331. Min Act: -0.0001

Data Index: 618520 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1102627 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1352. Min Act: -0.0001

Data Index: 392281 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1344. Min Act: -0.0001

Data Index: 870247 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1286. Min Act: -0.0001

Data Index: 860994 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1375. Min Act: -0.0001

Data Index: 882429 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1219. Min Act: -0.0001

Data Index: 560447 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1186. Min Act: -0.0001

Data Index: 608918 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1180. Min Act: -0.0001

Data Index: 568776 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1229. Min Act: -0.0001

Data Index: 766273 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1165914 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1266. Min Act: -0.0001

Data Index: 788077 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1053660 (C4 (Web Text))

Max Activating Token Index: 830