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

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

Neuron 3253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4675. Min Act: -0.0000

Data Index: 42084 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2120. Min Act: -0.0000

Data Index: 1185666 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.2881. Min Act: -0.0000

Data Index: 735761 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.1486. Min Act: -0.0000

Data Index: 201815 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.1856. Min Act: -0.0000

Data Index: 1041028 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.0508. Min Act: -0.0000

Data Index: 466941 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.0580. Min Act: -0.0000

Data Index: 605345 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.0348. Min Act: -0.0000

Data Index: 1177953 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.9685. Min Act: -0.0000

Data Index: 1199512 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.7821. Min Act: -0.0000

Data Index: 1229276 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.6478. Min Act: -0.0000

Data Index: 1091166 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.7239. Min Act: -0.0000

Data Index: 295981 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.8971. Min Act: -0.0000

Data Index: 820028 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.7233. Min Act: -0.0000

Data Index: 643803 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.4254. Min Act: -0.0000

Data Index: 803906 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.6271. Min Act: -0.0001

Data Index: 672694 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.5169. Min Act: -0.0000

Data Index: 950414 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.3850. Min Act: -0.0000

Data Index: 561569 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.6417. Min Act: -0.0000

Data Index: 182816 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 4.4675. Min Range: -4.4675

Max Act: 3.5046. Min Act: -0.0000

Data Index: 667289 (C4 (Web Text))

Max Activating Token Index: 486