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

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

Neuron 4943 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1050581 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1290. Min Act: -0.0001

Data Index: 541358 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1225. Min Act: -0.0001

Data Index: 659672 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1297291 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1158. Min Act: -0.0001

Data Index: 421273 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1170. Min Act: -0.0001

Data Index: 699377 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1274859 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1190. Min Act: -0.0001

Data Index: 957015 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1239. Min Act: -0.0001

Data Index: 167880 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1100. Min Act: -0.0001

Data Index: 44400 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1230590 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1287258 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1085176 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1201528 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1202. Min Act: -0.0001

Data Index: 558228 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1049. Min Act: -0.0001

Data Index: 76938 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0984. Min Act: -0.0001

Data Index: 340467 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1030. Min Act: -0.0001

Data Index: 96594 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1139988 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1054. Min Act: -0.0001

Data Index: 107304 (C4 (Web Text))

Max Activating Token Index: 755