Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1540 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1605. Min Act: -0.0003

Data Index: 560316 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1342. Min Act: -0.0003

Data Index: 762567 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1255. Min Act: -0.0003

Data Index: 237600 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1220. Min Act: -0.0003

Data Index: 992916 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1212. Min Act: -0.0004

Data Index: 482968 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1197. Min Act: -0.0003

Data Index: 11321 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1171. Min Act: -0.0004

Data Index: 836372 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1109. Min Act: -0.0003

Data Index: 158370 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1121. Min Act: -0.0003

Data Index: 628348 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1125. Min Act: -0.0003

Data Index: 1213215 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1092. Min Act: -0.0003

Data Index: 791857 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1071. Min Act: -0.0003

Data Index: 260792 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1072. Min Act: -0.0003

Data Index: 1146906 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1100. Min Act: -0.0003

Data Index: 91745 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1074. Min Act: -0.0003

Data Index: 1209098 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1068. Min Act: -0.0003

Data Index: 1194159 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1077. Min Act: -0.0003

Data Index: 597895 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1067. Min Act: -0.0003

Data Index: 496804 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1057. Min Act: -0.0003

Data Index: 291956 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1056. Min Act: -0.0003

Data Index: 1198987 (C4 (Web Text))

Max Activating Token Index: 919