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

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

Neuron 2954 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1435. Min Act: -0.0001

Data Index: 941930 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1281. Min Act: -0.0001

Data Index: 431543 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1048740 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1144495 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1232. Min Act: -0.0001

Data Index: 442493 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1262800 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1266. Min Act: -0.0001

Data Index: 435367 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1181. Min Act: -0.0001

Data Index: 989670 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1138. Min Act: -0.0001

Data Index: 206579 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1098. Min Act: -0.0001

Data Index: 533156 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1178. Min Act: -0.0001

Data Index: 930208 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1021. Min Act: -0.0001

Data Index: 87282 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1142129 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1337701 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1138. Min Act: -0.0001

Data Index: 96672 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1083. Min Act: -0.0001

Data Index: 967954 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1118. Min Act: -0.0001

Data Index: 38635 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1133. Min Act: -0.0001

Data Index: 665357 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1057. Min Act: -0.0001

Data Index: 518558 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1215. Min Act: -0.0001

Data Index: 562051 (C4 (Web Text))

Max Activating Token Index: 931