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

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

Neuron 1249 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.9361. Min Act: -0.0000

Data Index: 642514 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8771. Min Act: -0.0000

Data Index: 1287849 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.7710. Min Act: -0.0000

Data Index: 1464758 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.5136. Min Act: -0.0000

Data Index: 312284 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.9186. Min Act: -0.0000

Data Index: 1418030 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.6369. Min Act: -0.0000

Data Index: 107346 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8926. Min Act: -0.0000

Data Index: 1127286 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.5851. Min Act: -0.0000

Data Index: 250496 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.5586. Min Act: -0.0000

Data Index: 737538 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.6668. Min Act: -0.0000

Data Index: 1482024 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.5465. Min Act: -0.0000

Data Index: 903989 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.6646. Min Act: -0.0000

Data Index: 737746 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.5348. Min Act: -0.0000

Data Index: 1540713 (Python Code)

Max Activating Token Index: 467

Text #13

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.2901. Min Act: -0.0000

Data Index: 211664 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.5240. Min Act: -0.0000

Data Index: 388991 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.3391. Min Act: -0.0000

Data Index: 890680 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.6442. Min Act: -0.0000

Data Index: 449948 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.3867. Min Act: -0.0000

Data Index: 13706 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.4814. Min Act: -0.0000

Data Index: 1625782 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.4856. Min Act: -0.0000

Data Index: 8724 (C4 (Web Text))

Max Activating Token Index: 263