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

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

Neuron 1068 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1246. Min Act: -0.0001

Data Index: 519901 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1208291 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1234. Min Act: -0.0001

Data Index: 942036 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1208. Min Act: -0.0001

Data Index: 538785 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1094. Min Act: -0.0001

Data Index: 272939 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1127. Min Act: -0.0001

Data Index: 78533 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1235842 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1208603 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1079. Min Act: -0.0001

Data Index: 244290 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0960. Min Act: -0.0001

Data Index: 450572 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1105. Min Act: -0.0001

Data Index: 397146 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1093. Min Act: -0.0001

Data Index: 858345 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1048. Min Act: -0.0001

Data Index: 219756 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1281458 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0990. Min Act: -0.0000

Data Index: 315329 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1052. Min Act: -0.0000

Data Index: 784314 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1011. Min Act: -0.0001

Data Index: 358823 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1293951 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1042. Min Act: -0.0001

Data Index: 698863 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0998. Min Act: -0.0001

Data Index: 461811 (C4 (Web Text))

Max Activating Token Index: 417