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

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

Neuron 229 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.6054. Min Act: -0.0000

Data Index: 684937 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4359. Min Act: -0.0000

Data Index: 693915 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4111. Min Act: -0.0000

Data Index: 178295 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.3241. Min Act: -0.0000

Data Index: 1138520 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0455. Min Act: -0.0000

Data Index: 391573 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1284709 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0822. Min Act: -0.0000

Data Index: 739934 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9913. Min Act: -0.0000

Data Index: 296375 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0066. Min Act: -0.0000

Data Index: 550975 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9324. Min Act: -0.0000

Data Index: 825317 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9742. Min Act: -0.0000

Data Index: 110522 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9663. Min Act: -0.0000

Data Index: 959964 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9018. Min Act: -0.0000

Data Index: 654031 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0002. Min Act: -0.0000

Data Index: 407998 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9349. Min Act: -0.0000

Data Index: 457244 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9318. Min Act: -0.0000

Data Index: 587061 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9096. Min Act: -0.0000

Data Index: 520365 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9295. Min Act: -0.0000

Data Index: 174791 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.8679. Min Act: -0.0000

Data Index: 54036 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.8679. Min Act: -0.0000

Data Index: 18604 (C4 (Web Text))

Max Activating Token Index: 762