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

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

Neuron 4406 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1009737 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1220314 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.3182. Min Act: -0.0000

Data Index: 501595 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.3461. Min Act: -0.0000

Data Index: 831459 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2994. Min Act: -0.0000

Data Index: 903965 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1266869 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.3141. Min Act: -0.0000

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2933. Min Act: -0.0000

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2989. Min Act: -0.0000

Data Index: 828052 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1274510 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2800. Min Act: -0.0000

Data Index: 519506 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1257761 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1241377 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2580. Min Act: -0.0000

Data Index: 537937 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2659. Min Act: -0.0000

Data Index: 540661 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1238228 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2691. Min Act: -0.0000

Data Index: 495461 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2584. Min Act: -0.0000

Data Index: 560788 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1194273 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.4836. Min Range: -0.4836

Max Act: 0.2365. Min Act: -0.0000

Data Index: 374089 (C4 (Web Text))

Max Activating Token Index: 186