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

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

Neuron 3850 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.3116. Min Range: -12.3116

Max Act: 12.3116. Min Act: -0.0000

Data Index: 1021079 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.9539. Min Act: -0.0000

Data Index: 937481 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.5684. Min Act: -0.0000

Data Index: 1206138 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.9487. Min Act: -0.0000

Data Index: 1154866 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.6742. Min Act: -0.0000

Data Index: 14606 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.6541. Min Act: -0.0000

Data Index: 43267 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.6529. Min Act: -0.0000

Data Index: 266906 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.5427. Min Act: -0.0000

Data Index: 144508 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.4513. Min Act: -0.0000

Data Index: 780145 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.5013. Min Act: -0.0000

Data Index: 767188 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.2193. Min Act: -0.0000

Data Index: 714400 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.2571. Min Act: -0.0000

Data Index: 1127194 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.3505. Min Act: -0.0000

Data Index: 438314 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.0447. Min Act: -0.0000

Data Index: 697856 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.0524. Min Act: -0.0000

Data Index: 666999 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.8759. Min Act: -0.0000

Data Index: 179815 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.2912. Min Act: -0.0000

Data Index: 692236 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.0972. Min Act: -0.0000

Data Index: 867788 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 12.3116. Min Range: -12.3116

Max Act: 11.2186. Min Act: -0.0000

Data Index: 1035501 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 12.3116. Min Range: -12.3116

Max Act: 10.9478. Min Act: -0.0000

Data Index: 569784 (C4 (Web Text))

Max Activating Token Index: 212