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

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

Neuron 110 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.9338. Min Act: -0.0002

Data Index: 1062058 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.9075. Min Act: -0.0002

Data Index: 1248354 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8996. Min Act: -0.0002

Data Index: 1177153 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8450. Min Act: -0.0002

Data Index: 444327 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8721. Min Act: -0.0002

Data Index: 249719 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8374. Min Act: -0.0002

Data Index: 559007 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7744. Min Act: -0.0002

Data Index: 146925 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.6668. Min Act: -0.0002

Data Index: 1319992 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7519. Min Act: -0.0002

Data Index: 459970 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7666. Min Act: -0.0002

Data Index: 1347720 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.8321. Min Act: -0.0002

Data Index: 305893 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7105. Min Act: -0.0002

Data Index: 1143724 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7796. Min Act: -0.0002

Data Index: 234561 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.6878. Min Act: -0.0002

Data Index: 756951 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7224. Min Act: -0.0002

Data Index: 370933 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7076. Min Act: -0.0002

Data Index: 616168 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7247. Min Act: -0.0002

Data Index: 938681 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7039. Min Act: -0.0002

Data Index: 1094463 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7911. Min Act: -0.0002

Data Index: 1173382 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.9338. Min Range: -0.9338

Max Act: 0.7410. Min Act: -0.0002

Data Index: 883847 (C4 (Web Text))

Max Activating Token Index: 109