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

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

Neuron 2374 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: 0.5872. Min Range: -0.5872

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1237208 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5204. Min Act: -0.0000

Data Index: 981717 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1117344 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5069. Min Act: -0.0000

Data Index: 135790 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.4184. Min Act: -0.0000

Data Index: 929561 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.4396. Min Act: -0.0000

Data Index: 987368 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1057504 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.4227. Min Act: -0.0000

Data Index: 186974 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3961. Min Act: -0.0000

Data Index: 302290 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3863. Min Act: 0.0000

Data Index: 1567399 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3756. Min Act: -0.0000

Data Index: 960459 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3949. Min Act: -0.0000

Data Index: 842122 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3728. Min Act: -0.0000

Data Index: 789763 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3722. Min Act: -0.0000

Data Index: 370777 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3534. Min Act: -0.0000

Data Index: 711553 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1494935 (Python Code)

Max Activating Token Index: 415

Text #16

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1120475 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3426. Min Act: 0.0000

Data Index: 514045 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1325473 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1549736 (Python Code)

Max Activating Token Index: 692