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

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

Neuron 1046 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: 0.1235. Min Range: -0.1235

Max Act: 0.1235. Min Act: -0.0004

Data Index: 1047280 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1123. Min Act: -0.0004

Data Index: 520560 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1167. Min Act: -0.0004

Data Index: 1158152 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0990. Min Act: -0.0004

Data Index: 815198 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1157. Min Act: -0.0004

Data Index: 325325 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1201. Min Act: -0.0004

Data Index: 813051 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1090. Min Act: -0.0004

Data Index: 136003 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1230. Min Act: -0.0004

Data Index: 545960 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1048. Min Act: -0.0004

Data Index: 393519 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1064. Min Act: -0.0004

Data Index: 95842 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1142. Min Act: -0.0004

Data Index: 430723 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0981. Min Act: -0.0004

Data Index: 979537 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0937. Min Act: -0.0004

Data Index: 95566 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0941. Min Act: -0.0004

Data Index: 1302373 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0934. Min Act: -0.0004

Data Index: 786457 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0951. Min Act: -0.0004

Data Index: 544463 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0924. Min Act: -0.0004

Data Index: 178312 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0991. Min Act: -0.0004

Data Index: 674101 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0989. Min Act: -0.0004

Data Index: 227865 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0953. Min Act: -0.0004

Data Index: 441166 (C4 (Web Text))

Max Activating Token Index: 329