Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 67 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1055. Min Act: -0.0001

Data Index: 53956 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1226. Min Act: -0.0001

Data Index: 228139 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1117. Min Act: -0.0001

Data Index: 910946 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0918. Min Act: -0.0001

Data Index: 263336 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1095763 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1263. Min Act: -0.0001

Data Index: 945225 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1227. Min Act: -0.0001

Data Index: 468994 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1074. Min Act: -0.0001

Data Index: 215087 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0962. Min Act: -0.0001

Data Index: 881658 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1030. Min Act: -0.0001

Data Index: 575712 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1328906 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1055. Min Act: -0.0001

Data Index: 767244 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0847. Min Act: -0.0001

Data Index: 581844 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1079. Min Act: -0.0001

Data Index: 828475 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1085. Min Act: -0.0001

Data Index: 894531 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0940. Min Act: -0.0001

Data Index: 417128 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1220113 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1334023 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1067. Min Act: -0.0001

Data Index: 588660 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1255468 (C4 (Web Text))

Max Activating Token Index: 671