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

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

Neuron 1570 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: 2.9015. Min Range: -2.9015

Max Act: 2.9015. Min Act: -0.0000

Data Index: 547183 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.4875. Min Act: -0.0000

Data Index: 671197 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.6022. Min Act: -0.0000

Data Index: 1223440 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.3440. Min Act: -0.0000

Data Index: 559018 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.3056. Min Act: -0.0000

Data Index: 774377 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.2642. Min Act: -0.0000

Data Index: 611106 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.2474. Min Act: -0.0000

Data Index: 304438 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.2434. Min Act: -0.0000

Data Index: 877888 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.1580. Min Act: -0.0000

Data Index: 698872 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.1011. Min Act: -0.0000

Data Index: 523801 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.1094. Min Act: -0.0000

Data Index: 628028 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.0850. Min Act: -0.0000

Data Index: 659833 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.0554. Min Act: -0.0000

Data Index: 1033628 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.0236. Min Act: -0.0000

Data Index: 809313 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.0325. Min Act: -0.0000

Data Index: 676320 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.1359. Min Act: -0.0000

Data Index: 336267 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 2.9015. Min Range: -2.9015

Max Act: 1.9913. Min Act: -0.0000

Data Index: 660706 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 2.9015. Min Range: -2.9015

Max Act: 1.9808. Min Act: -0.0000

Data Index: 1301655 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 2.9015. Min Range: -2.9015

Max Act: 2.0826. Min Act: -0.0000

Data Index: 671387 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 2.9015. Min Range: -2.9015

Max Act: 1.9825. Min Act: -0.0000

Data Index: 294853 (C4 (Web Text))

Max Activating Token Index: 247