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

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

Neuron 3226 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2187. Min Act: -0.0002

Data Index: 521756 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2353. Min Act: -0.0002

Data Index: 1256045 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1206087 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1321. Min Act: -0.0002

Data Index: 1069483 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1262. Min Act: -0.0002

Data Index: 515434 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1239. Min Act: -0.0002

Data Index: 278946 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1187. Min Act: -0.0002

Data Index: 899983 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1275. Min Act: -0.0002

Data Index: 632596 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1244. Min Act: -0.0002

Data Index: 623200 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1101. Min Act: -0.0002

Data Index: 214902 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1098. Min Act: -0.0002

Data Index: 564080 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1080. Min Act: -0.0002

Data Index: 296952 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1081. Min Act: -0.0002

Data Index: 921778 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1227270 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1095673 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1102. Min Act: -0.0002

Data Index: 338359 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1014. Min Act: -0.0002

Data Index: 122630 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1047. Min Act: -0.0002

Data Index: 612596 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1091370 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1050. Min Act: -0.0002

Data Index: 837759 (C4 (Web Text))

Max Activating Token Index: 986