Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2918 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1628720 (Python Code)

Max Activating Token Index: 757

Text #1

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4638. Min Act: -0.0000

Data Index: 38313 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4321. Min Act: -0.0000

Data Index: 177974 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4619. Min Act: -0.0000

Data Index: 356835 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4226. Min Act: -0.0000

Data Index: 287151 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3934. Min Act: -0.0000

Data Index: 896811 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1566407 (Python Code)

Max Activating Token Index: 388

Text #7

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1523599 (Python Code)

Max Activating Token Index: 727

Text #8

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1582255 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3838. Min Act: -0.0000

Data Index: 321269 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1609046 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4096. Min Act: -0.0000

Data Index: 319573 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4128. Min Act: -0.0000

Data Index: 584431 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3958. Min Act: -0.0000

Data Index: 302600 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1077638 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3648. Min Act: -0.0000

Data Index: 286209 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1386838 (Python Code)

Max Activating Token Index: 804

Text #17

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3821. Min Act: -0.0000

Data Index: 251458 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1417715 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3530. Min Act: -0.0000

Data Index: 82067 (C4 (Web Text))

Max Activating Token Index: 603