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

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

Neuron 1661 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: 5.2660. Min Range: -5.2660

Max Act: 5.2660. Min Act: -0.0000

Data Index: 409367 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.6518. Min Act: -0.0000

Data Index: 583735 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.1201. Min Act: -0.0000

Data Index: 826010 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.0794. Min Act: -0.0000

Data Index: 271932 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.9040. Min Act: -0.0000

Data Index: 258873 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.8055. Min Act: -0.0000

Data Index: 898769 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.5453. Min Act: -0.0000

Data Index: 32151 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.8800. Min Act: -0.0000

Data Index: 287215 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.8703. Min Act: -0.0000

Data Index: 1251454 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.6087. Min Act: -0.0000

Data Index: 365385 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.5452. Min Act: -0.0000

Data Index: 1338985 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.3537. Min Act: -0.0000

Data Index: 910324 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.3200. Min Act: -0.0000

Data Index: 1183780 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.3027. Min Act: -0.0000

Data Index: 438995 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.4096. Min Act: -0.0000

Data Index: 715560 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.3911. Min Act: -0.0000

Data Index: 702446 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.2642. Min Act: -0.0000

Data Index: 60411 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.2185. Min Act: -0.0000

Data Index: 166874 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 5.2660. Min Range: -5.2660

Max Act: 2.9934. Min Act: -0.0000

Data Index: 269204 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 5.2660. Min Range: -5.2660

Max Act: 2.9464. Min Act: -0.0000

Data Index: 1164655 (C4 (Web Text))

Max Activating Token Index: 629