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

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

Neuron 609 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1182. Min Act: -0.0001

Data Index: 881324 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1036. Min Act: -0.0001

Data Index: 821103 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1027. Min Act: -0.0001

Data Index: 450727 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1009. Min Act: -0.0001

Data Index: 307755 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0993. Min Act: -0.0001

Data Index: 704522 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1019398 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0983. Min Act: -0.0001

Data Index: 733856 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0954. Min Act: -0.0001

Data Index: 353654 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0930. Min Act: -0.0001

Data Index: 659077 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0949. Min Act: -0.0001

Data Index: 816673 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1344969 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0940. Min Act: -0.0001

Data Index: 56676 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0940. Min Act: -0.0001

Data Index: 340314 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1050507 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0907. Min Act: -0.0001

Data Index: 434799 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0919. Min Act: -0.0001

Data Index: 795930 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1066381 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1029445 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0883. Min Act: -0.0001

Data Index: 412716 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1094819 (C4 (Web Text))

Max Activating Token Index: 9