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

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

Neuron 185 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7964. Min Range: -4.7964

Max Act: 4.7964. Min Act: -0.0000

Data Index: 858087 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 4.7964. Min Range: -4.7964

Max Act: 4.2143. Min Act: -0.0000

Data Index: 981200 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 4.7964. Min Range: -4.7964

Max Act: 4.1553. Min Act: -0.0000

Data Index: 1164302 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.8753. Min Act: -0.0000

Data Index: 293686 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.6840. Min Act: -0.0000

Data Index: 42226 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.7624. Min Act: -0.0000

Data Index: 751493 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.6852. Min Act: -0.0000

Data Index: 1147397 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.4874. Min Act: -0.0000

Data Index: 1159460 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.7643. Min Act: -0.0000

Data Index: 1048386 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.4800. Min Act: -0.0000

Data Index: 2676 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.7110. Min Act: -0.0000

Data Index: 585930 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.6637. Min Act: -0.0000

Data Index: 19087 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.5084. Min Act: -0.0000

Data Index: 520152 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 4.7964. Min Range: -4.7964

Max Act: 2.9885. Min Act: -0.0000

Data Index: 91763 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.1028. Min Act: -0.0000

Data Index: 148884 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.4302. Min Act: -0.0000

Data Index: 993473 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 4.7964. Min Range: -4.7964

Max Act: 2.9936. Min Act: -0.0000

Data Index: 658843 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.3533. Min Act: -0.0000

Data Index: 972767 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 4.7964. Min Range: -4.7964

Max Act: 3.1596. Min Act: -0.0000

Data Index: 369775 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 4.7964. Min Range: -4.7964

Max Act: 2.8413. Min Act: -0.0000

Data Index: 621085 (C4 (Web Text))

Max Activating Token Index: 599