Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 499 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3022. Min Range: -1.3022

Max Act: 1.3022. Min Act: -0.0000

Data Index: 99208 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 1.3022. Min Range: -1.3022

Max Act: 1.2026. Min Act: -0.0000

Data Index: 689103 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 1.3022. Min Range: -1.3022

Max Act: 1.1008. Min Act: -0.0000

Data Index: 211934 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 1.3022. Min Range: -1.3022

Max Act: 1.0141. Min Act: -0.0001

Data Index: 835967 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.3022. Min Range: -1.3022

Max Act: 1.0757. Min Act: -0.0001

Data Index: 1165968 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 1.3022. Min Range: -1.3022

Max Act: 1.0544. Min Act: -0.0001

Data Index: 84321 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 1.3022. Min Range: -1.3022

Max Act: 1.0237. Min Act: -0.0000

Data Index: 806871 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.3022. Min Range: -1.3022

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1294373 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.9738. Min Act: -0.0001

Data Index: 349396 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.9972. Min Act: -0.0000

Data Index: 827008 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.9550. Min Act: -0.0000

Data Index: 863750 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.8010. Min Act: -0.0001

Data Index: 439024 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.8518. Min Act: -0.0000

Data Index: 165795 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.9009. Min Act: -0.0000

Data Index: 620971 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.8898. Min Act: -0.0000

Data Index: 499301 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.8773. Min Act: -0.0000

Data Index: 133913 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.8485. Min Act: -0.0000

Data Index: 765708 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.7935. Min Act: -0.0000

Data Index: 986220 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.8139. Min Act: -0.0000

Data Index: 831944 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 1.3022. Min Range: -1.3022

Max Act: 0.8348. Min Act: -0.0001

Data Index: 765763 (C4 (Web Text))

Max Activating Token Index: 657