Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1897 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0005

Data Index: 453931 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1186. Min Act: -0.0005

Data Index: 952164 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1237. Min Act: -0.0005

Data Index: 30166 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1122. Min Act: -0.0005

Data Index: 1050429 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1112. Min Act: -0.0005

Data Index: 251251 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1151. Min Act: -0.0005

Data Index: 738864 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1193. Min Act: -0.0005

Data Index: 682079 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1028. Min Act: -0.0005

Data Index: 291162 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1105. Min Act: -0.0005

Data Index: 322815 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1094. Min Act: -0.0005

Data Index: 910421 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1059. Min Act: -0.0005

Data Index: 597121 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0999. Min Act: -0.0005

Data Index: 1028772 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1034. Min Act: -0.0005

Data Index: 410907 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0988. Min Act: -0.0004

Data Index: 422324 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0953. Min Act: -0.0005

Data Index: 417261 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1011. Min Act: -0.0005

Data Index: 645580 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0861. Min Act: -0.0004

Data Index: 30607 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1046. Min Act: -0.0005

Data Index: 318144 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0962. Min Act: -0.0005

Data Index: 893351 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0979. Min Act: -0.0005

Data Index: 229251 (C4 (Web Text))

Max Activating Token Index: 84