Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 112 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3503. Min Act: -0.0000

Data Index: 361310 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3412. Min Act: -0.0000

Data Index: 727983 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3483. Min Act: -0.0000

Data Index: 180964 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3130. Min Act: -0.0000

Data Index: 985082 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2954. Min Act: -0.0000

Data Index: 724078 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2682. Min Act: -0.0000

Data Index: 997074 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1061448 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2972. Min Act: -0.0000

Data Index: 260530 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2954. Min Act: -0.0000

Data Index: 133412 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2753. Min Act: -0.0000

Data Index: 138310 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2828. Min Act: -0.0000

Data Index: 86745 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2747. Min Act: -0.0000

Data Index: 376519 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1309865 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3012. Min Act: -0.0000

Data Index: 819523 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2908. Min Act: -0.0000

Data Index: 653649 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2868. Min Act: -0.0000

Data Index: 171182 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2673. Min Act: -0.0000

Data Index: 160218 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2656. Min Act: -0.0000

Data Index: 371684 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2852. Min Act: -0.0000

Data Index: 602162 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2707. Min Act: -0.0000

Data Index: 349954 (C4 (Web Text))

Max Activating Token Index: 222