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

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

Neuron 6090 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4069. Min Range: -8.4069

Max Act: 8.4069. Min Act: 0.0000

Data Index: 1323779 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 8.4069. Min Range: -8.4069

Max Act: 7.6195. Min Act: 0.0000

Data Index: 472345 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 8.4069. Min Range: -8.4069

Max Act: 7.3566. Min Act: -0.0000

Data Index: 458520 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 8.4069. Min Range: -8.4069

Max Act: 7.2941. Min Act: -0.0000

Data Index: 768048 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 8.4069. Min Range: -8.4069

Max Act: 7.2427. Min Act: -0.0000

Data Index: 1251531 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 8.4069. Min Range: -8.4069

Max Act: 7.3159. Min Act: -0.0000

Data Index: 1067131 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 8.4069. Min Range: -8.4069

Max Act: 7.3392. Min Act: -0.0000

Data Index: 370190 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 8.4069. Min Range: -8.4069

Max Act: 7.0647. Min Act: -0.0000

Data Index: 999458 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.6337. Min Act: 0.0000

Data Index: 880933 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.7575. Min Act: -0.0000

Data Index: 525632 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.7361. Min Act: -0.0000

Data Index: 903797 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.7140. Min Act: -0.0000

Data Index: 264310 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.7740. Min Act: -0.0000

Data Index: 760013 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.5682. Min Act: -0.0000

Data Index: 996749 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.5404. Min Act: -0.0000

Data Index: 1101756 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.3035. Min Act: -0.0000

Data Index: 493300 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.2704. Min Act: -0.0000

Data Index: 311815 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.4812. Min Act: -0.0000

Data Index: 297640 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.2134. Min Act: -0.0000

Data Index: 187884 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 8.4069. Min Range: -8.4069

Max Act: 6.0641. Min Act: 0.0000

Data Index: 1213431 (C4 (Web Text))

Max Activating Token Index: 227