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

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

Neuron 3021 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7060. Min Range: -6.7060

Max Act: 6.7060. Min Act: -0.0000

Data Index: 1333072 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 6.7060. Min Range: -6.7060

Max Act: 5.9939. Min Act: 0.0000

Data Index: 539058 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 6.7060. Min Range: -6.7060

Max Act: 5.9085. Min Act: -0.0000

Data Index: 1062833 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 6.7060. Min Range: -6.7060

Max Act: 5.5790. Min Act: -0.0000

Data Index: 1027780 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 6.7060. Min Range: -6.7060

Max Act: 5.3364. Min Act: -0.0000

Data Index: 992235 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.9836. Min Act: -0.0000

Data Index: 1262152 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.8682. Min Act: -0.0000

Data Index: 512099 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 6.7060. Min Range: -6.7060

Max Act: 5.0077. Min Act: -0.0000

Data Index: 530901 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.7478. Min Act: -0.0000

Data Index: 745067 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.9081. Min Act: -0.0000

Data Index: 142364 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.8972. Min Act: -0.0000

Data Index: 79537 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.5327. Min Act: -0.0000

Data Index: 560699 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.5214. Min Act: -0.0000

Data Index: 710437 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.4483. Min Act: -0.0000

Data Index: 1308186 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.4408. Min Act: -0.0000

Data Index: 225479 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.4673. Min Act: -0.0000

Data Index: 932526 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.6095. Min Act: -0.0000

Data Index: 1069833 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.5916. Min Act: -0.0000

Data Index: 1205537 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.5821. Min Act: -0.0000

Data Index: 558209 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 6.7060. Min Range: -6.7060

Max Act: 4.5822. Min Act: -0.0000

Data Index: 798091 (C4 (Web Text))

Max Activating Token Index: 23