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

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

Neuron 1105 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8744. Min Act: -0.0001

Data Index: 65600 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8088. Min Act: -0.0001

Data Index: 1076953 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7982. Min Act: -0.0001

Data Index: 2071 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7893. Min Act: -0.0001

Data Index: 472934 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7823. Min Act: -0.0001

Data Index: 457131 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7755. Min Act: -0.0001

Data Index: 1211196 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7633. Min Act: -0.0001

Data Index: 794212 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7326. Min Act: -0.0001

Data Index: 21591 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1288632 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7734. Min Act: -0.0001

Data Index: 184397 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7801. Min Act: -0.0001

Data Index: 1315570 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1235330 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7402. Min Act: -0.0001

Data Index: 552787 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7153. Min Act: -0.0001

Data Index: 1309602 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7363. Min Act: -0.0001

Data Index: 743896 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7317. Min Act: -0.0001

Data Index: 916451 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6991. Min Act: -0.0001

Data Index: 615235 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7015. Min Act: -0.0001

Data Index: 787810 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7220. Min Act: -0.0001

Data Index: 928253 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7148. Min Act: -0.0001

Data Index: 256769 (C4 (Web Text))

Max Activating Token Index: 490