Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3988 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1399. Min Act: -0.0002

Data Index: 773355 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1217. Min Act: -0.0001

Data Index: 595784 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1188464 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1235258 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1201221 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1245741 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0998. Min Act: -0.0001

Data Index: 524139 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0993. Min Act: -0.0001

Data Index: 187566 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0969. Min Act: -0.0001

Data Index: 42558 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0971. Min Act: -0.0002

Data Index: 54448 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1287779 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1223714 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1194750 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1295865 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0906. Min Act: -0.0001

Data Index: 835770 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1140630 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0861. Min Act: -0.0001

Data Index: 872131 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0879. Min Act: -0.0001

Data Index: 495214 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1407215 (Python Code)

Max Activating Token Index: 92

Text #19

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.0814. Min Act: -0.0001

Data Index: 720666 (C4 (Web Text))

Max Activating Token Index: 831