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

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

Neuron 2225 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0467. Min Range: -1.0467

Max Act: 1.0467. Min Act: -0.0001

Data Index: 1269384 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9858. Min Act: -0.0002

Data Index: 413427 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9836. Min Act: -0.0002

Data Index: 1141414 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9719. Min Act: -0.0001

Data Index: 772950 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9484. Min Act: -0.0001

Data Index: 10901 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9424. Min Act: -0.0001

Data Index: 1083962 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9240. Min Act: -0.0001

Data Index: 1188924 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8934. Min Act: -0.0002

Data Index: 774534 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9178. Min Act: -0.0002

Data Index: 1078749 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8546. Min Act: -0.0001

Data Index: 708613 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9039. Min Act: -0.0002

Data Index: 1185726 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8490. Min Act: -0.0002

Data Index: 1323239 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8555. Min Act: -0.0001

Data Index: 539977 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8212. Min Act: -0.0002

Data Index: 895188 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8146. Min Act: -0.0002

Data Index: 1276152 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8864. Min Act: -0.0002

Data Index: 424008 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8297. Min Act: -0.0002

Data Index: 794060 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8800. Min Act: -0.0001

Data Index: 1254377 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8692. Min Act: -0.0002

Data Index: 1259950 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8517. Min Act: -0.0002

Data Index: 288147 (C4 (Web Text))

Max Activating Token Index: 895