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

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

Neuron 899 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.8136. Min Act: -0.0000

Data Index: 908378 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.5945. Min Act: -0.0000

Data Index: 528794 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.3135. Min Act: -0.0000

Data Index: 1095217 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.2016. Min Act: -0.0000

Data Index: 826160 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1328666 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.0126. Min Act: -0.0000

Data Index: 42295 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1125822 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1028587 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1327244 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.8992. Min Act: -0.0000

Data Index: 49872 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.0288. Min Act: -0.0000

Data Index: 316551 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1277661 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1015194 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.9755. Min Act: -0.0000

Data Index: 633026 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1310729 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.9587. Min Act: -0.0000

Data Index: 712546 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.9996. Min Act: -0.0000

Data Index: 923912 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.8704. Min Act: -0.0000

Data Index: 151284 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.7632. Min Act: -0.0000

Data Index: 919222 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.8136. Min Range: -1.8136

Max Act: 0.8137. Min Act: -0.0000

Data Index: 181667 (C4 (Web Text))

Max Activating Token Index: 810