Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1997 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3299. Min Act: -0.0003

Data Index: 857313 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3258. Min Act: -0.0003

Data Index: 1266827 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3149. Min Act: -0.0003

Data Index: 549177 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3150. Min Act: -0.0003

Data Index: 585648 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3077. Min Act: -0.0003

Data Index: 1132626 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3014. Min Act: -0.0003

Data Index: 1017912 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2952. Min Act: -0.0004

Data Index: 220280 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2957. Min Act: -0.0003

Data Index: 557763 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3113. Min Act: -0.0003

Data Index: 820407 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2791. Min Act: -0.0003

Data Index: 1217891 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2855. Min Act: -0.0003

Data Index: 717892 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2876. Min Act: -0.0003

Data Index: 315762 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2845. Min Act: -0.0003

Data Index: 1249899 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2948. Min Act: -0.0003

Data Index: 168378 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2841. Min Act: -0.0003

Data Index: 611594 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2833. Min Act: -0.0003

Data Index: 1094050 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2940. Min Act: -0.0004

Data Index: 1055007 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2820. Min Act: -0.0003

Data Index: 1144072 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2668. Min Act: -0.0003

Data Index: 49968 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2693. Min Act: -0.0003

Data Index: 1277748 (C4 (Web Text))

Max Activating Token Index: 777