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

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

Neuron 1990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1167721 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0896. Min Act: -0.0000

Data Index: 998389 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1138261 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0789. Min Act: -0.0001

Data Index: 282102 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0744. Min Act: -0.0001

Data Index: 705454 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0747. Min Act: -0.0001

Data Index: 218696 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1149995 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1160470 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0711. Min Act: -0.0001

Data Index: 97431 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0725. Min Act: -0.0001

Data Index: 317229 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0714. Min Act: -0.0001

Data Index: 318254 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1108182 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0677. Min Act: -0.0000

Data Index: 878299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0699. Min Act: -0.0000

Data Index: 1407543 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0723. Min Act: -0.0001

Data Index: 908040 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1076443 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1204239 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1110148 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1482432 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1335771 (C4 (Web Text))

Max Activating Token Index: 603