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

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

Neuron 4667 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1070. Min Act: -0.0002

Data Index: 399066 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1013. Min Act: -0.0003

Data Index: 629157 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1254531 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0930. Min Act: -0.0002

Data Index: 564581 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1090215 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0940. Min Act: -0.0003

Data Index: 644804 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0928. Min Act: -0.0002

Data Index: 92517 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0922. Min Act: -0.0002

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0864. Min Act: -0.0002

Data Index: 41181 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0862. Min Act: -0.0002

Data Index: 895745 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0811. Min Act: -0.0002

Data Index: 124667 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0849. Min Act: -0.0002

Data Index: 174285 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0851. Min Act: -0.0003

Data Index: 1120429 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0815. Min Act: -0.0002

Data Index: 404920 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0816. Min Act: -0.0002

Data Index: 975948 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0811. Min Act: -0.0003

Data Index: 82839 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0854. Min Act: -0.0002

Data Index: 602864 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1268511 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0817. Min Act: -0.0002

Data Index: 788287 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1265574 (C4 (Web Text))

Max Activating Token Index: 662