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

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

Neuron 1409 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3924. Min Act: -0.0000

Data Index: 447687 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3380. Min Act: -0.0000

Data Index: 94120 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1080948 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3059. Min Act: 0.0001

Data Index: 1170452 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2969. Min Act: -0.0000

Data Index: 516642 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3143. Min Act: -0.0000

Data Index: 223290 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3219. Min Act: -0.0000

Data Index: 643957 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1015351 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2969. Min Act: 0.0000

Data Index: 1172837 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2818. Min Act: -0.0000

Data Index: 28797 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1261481 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3072. Min Act: -0.0000

Data Index: 504122 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2840. Min Act: 0.0002

Data Index: 277141 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2821. Min Act: 0.0000

Data Index: 1269689 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2926. Min Act: 0.0000

Data Index: 633555 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1002959 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1208664 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1319965 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2760. Min Act: -0.0000

Data Index: 499221 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1001181 (C4 (Web Text))

Max Activating Token Index: 78