Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4749 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.1263. Min Act: -0.0001

Data Index: 478742 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.1094. Min Act: -0.0001

Data Index: 164715 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.1287. Min Act: -0.0001

Data Index: 577326 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.0869. Min Act: -0.0001

Data Index: 742983 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.0045. Min Act: -0.0001

Data Index: 427571 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.0848. Min Act: -0.0000

Data Index: 1104568 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9409. Min Act: -0.0001

Data Index: 482127 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9954. Min Act: -0.0001

Data Index: 726858 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9597. Min Act: -0.0001

Data Index: 1110856 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.8864. Min Act: -0.0001

Data Index: 241016 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.8793. Min Act: -0.0001

Data Index: 119607 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9080. Min Act: -0.0001

Data Index: 850147 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.8678. Min Act: -0.0001

Data Index: 1098573 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9176. Min Act: -0.0001

Data Index: 966872 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.8949. Min Act: -0.0001

Data Index: 1186530 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.8805. Min Act: -0.0001

Data Index: 163933 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9034. Min Act: -0.0001

Data Index: 1094574 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9004. Min Act: -0.0001

Data Index: 749944 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 1.1287. Min Range: -1.1287

Max Act: 1.0056. Min Act: -0.0001

Data Index: 422992 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 1.1287. Min Range: -1.1287

Max Act: 0.9088. Min Act: -0.0001

Data Index: 824815 (C4 (Web Text))

Max Activating Token Index: 718