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

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

Neuron 385 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1302. Min Act: -0.0003

Data Index: 216933 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0003

Data Index: 798472 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1005. Min Act: -0.0003

Data Index: 334603 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1256. Min Act: -0.0003

Data Index: 516133 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1154. Min Act: -0.0003

Data Index: 1348314 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1113. Min Act: -0.0003

Data Index: 167601 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1157. Min Act: -0.0003

Data Index: 1081351 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1142. Min Act: -0.0003

Data Index: 1019892 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1094. Min Act: -0.0003

Data Index: 701269 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0977. Min Act: -0.0003

Data Index: 338548 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1089. Min Act: -0.0003

Data Index: 22132 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1046. Min Act: -0.0003

Data Index: 1226420 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1160. Min Act: -0.0003

Data Index: 585283 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1183. Min Act: -0.0003

Data Index: 609005 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1098. Min Act: -0.0003

Data Index: 356077 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1094. Min Act: -0.0003

Data Index: 637825 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1133. Min Act: -0.0003

Data Index: 281426 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1032. Min Act: -0.0003

Data Index: 407100 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1091. Min Act: -0.0003

Data Index: 250299 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1007. Min Act: -0.0003

Data Index: 548654 (C4 (Web Text))

Max Activating Token Index: 154