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

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

Neuron 689 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4728. Min Range: -1.4728

Max Act: 1.4728. Min Act: -0.0000

Data Index: 875641 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 1.4728. Min Range: -1.4728

Max Act: 1.3735. Min Act: -0.0000

Data Index: 62779 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.4728. Min Range: -1.4728

Max Act: 1.0428. Min Act: -0.0000

Data Index: 476023 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 1.4728. Min Range: -1.4728

Max Act: 1.0898. Min Act: -0.0000

Data Index: 203757 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 1.4728. Min Range: -1.4728

Max Act: 1.0200. Min Act: -0.0000

Data Index: 1305545 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.9471. Min Act: -0.0000

Data Index: 167648 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.9143. Min Act: -0.0000

Data Index: 270977 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8384. Min Act: -0.0000

Data Index: 699641 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7690. Min Act: -0.0000

Data Index: 892807 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1251939 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1089087 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1261965 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8614. Min Act: -0.0000

Data Index: 652668 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8158. Min Act: 0.0000

Data Index: 802272 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8469. Min Act: -0.0000

Data Index: 667132 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7957. Min Act: -0.0000

Data Index: 683283 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1313304 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8165. Min Act: -0.0000

Data Index: 93374 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8225. Min Act: -0.0000

Data Index: 742412 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7831. Min Act: -0.0000

Data Index: 420537 (C4 (Web Text))

Max Activating Token Index: 84