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

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

Neuron 4468 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.2005. Min Act: -0.0000

Data Index: 586914 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1862. Min Act: -0.0000

Data Index: 594648 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1063184 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1904. Min Act: -0.0000

Data Index: 423141 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1913. Min Act: -0.0000

Data Index: 601456 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1477. Min Act: -0.0000

Data Index: 949976 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1217. Min Act: -0.0000

Data Index: 121467 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.0874. Min Act: -0.0000

Data Index: 711265 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1092. Min Act: -0.0000

Data Index: 81255 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1047. Min Act: -0.0000

Data Index: 19303 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.0945. Min Act: -0.0000

Data Index: 43562 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.0896. Min Act: -0.0000

Data Index: 419600 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1020. Min Act: -0.0000

Data Index: 125706 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1017. Min Act: -0.0001

Data Index: 1190109 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.0977. Min Act: -0.0000

Data Index: 108603 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1060601 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.0946. Min Act: -0.0000

Data Index: 226702 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.0908. Min Act: -0.0001

Data Index: 930452 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.0900. Min Act: -0.0000

Data Index: 404053 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.0833. Min Act: -0.0000

Data Index: 368971 (C4 (Web Text))

Max Activating Token Index: 145