Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1841 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8703. Min Act: -0.0003

Data Index: 335513 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8111. Min Act: -0.0003

Data Index: 1131589 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8869. Min Act: -0.0003

Data Index: 678925 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8137. Min Act: -0.0003

Data Index: 1194350 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8180. Min Act: -0.0003

Data Index: 616515 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7238. Min Act: -0.0003

Data Index: 1209909 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8012. Min Act: -0.0003

Data Index: 153840 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7956. Min Act: -0.0003

Data Index: 1316295 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7986. Min Act: -0.0003

Data Index: 340217 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7922. Min Act: -0.0003

Data Index: 1322314 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7793. Min Act: -0.0003

Data Index: 196385 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7000. Min Act: -0.0003

Data Index: 1236437 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7583. Min Act: -0.0003

Data Index: 725215 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7516. Min Act: -0.0003

Data Index: 248932 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7987. Min Act: -0.0003

Data Index: 937046 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7559. Min Act: -0.0003

Data Index: 273946 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7585. Min Act: -0.0003

Data Index: 1195801 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7196. Min Act: -0.0003

Data Index: 64332 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7833. Min Act: -0.0003

Data Index: 309374 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7390. Min Act: -0.0003

Data Index: 769214 (C4 (Web Text))

Max Activating Token Index: 794