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

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

Neuron 595 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.7440. Min Act: -0.0000

Data Index: 182851 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5221. Min Act: -0.0001

Data Index: 754254 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5550. Min Act: -0.0001

Data Index: 473636 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1306539 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4853. Min Act: -0.0001

Data Index: 604947 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1151826 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5081. Min Act: -0.0001

Data Index: 939450 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4745. Min Act: -0.0001

Data Index: 921246 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4757. Min Act: -0.0001

Data Index: 1245846 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1216210 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4678. Min Act: -0.0000

Data Index: 3595 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1351643 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4694. Min Act: -0.0001

Data Index: 1194825 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4746. Min Act: -0.0001

Data Index: 672705 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4384. Min Act: -0.0000

Data Index: 724277 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4976. Min Act: -0.0000

Data Index: 424492 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4836. Min Act: -0.0001

Data Index: 700807 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4267. Min Act: -0.0001

Data Index: 794240 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4652. Min Act: -0.0001

Data Index: 849284 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4543. Min Act: -0.0001

Data Index: 515613 (C4 (Web Text))

Max Activating Token Index: 939