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

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

Neuron 800 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.7755. Min Act: -0.0001

Data Index: 1292070 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.7914. Min Act: -0.0001

Data Index: 895241 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.7345. Min Act: -0.0001

Data Index: 131098 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.7239. Min Act: -0.0001

Data Index: 1179482 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5489. Min Act: -0.0001

Data Index: 107918 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6813. Min Act: -0.0001

Data Index: 1066312 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5583. Min Act: -0.0001

Data Index: 223042 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6169. Min Act: -0.0001

Data Index: 594176 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5846. Min Act: -0.0001

Data Index: 865091 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5984. Min Act: -0.0001

Data Index: 416021 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5616. Min Act: -0.0001

Data Index: 1351059 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5937. Min Act: -0.0001

Data Index: 104667 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6316. Min Act: -0.0001

Data Index: 652567 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.6057. Min Act: -0.0001

Data Index: 1280049 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5873. Min Act: -0.0001

Data Index: 879398 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5826. Min Act: -0.0001

Data Index: 159823 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5716. Min Act: -0.0001

Data Index: 200749 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5726. Min Act: -0.0001

Data Index: 785041 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5567. Min Act: -0.0001

Data Index: 901270 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.7914. Min Range: -0.7914

Max Act: 0.5429. Min Act: -0.0001

Data Index: 817850 (C4 (Web Text))

Max Activating Token Index: 49