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

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

Neuron 3952 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1452. Min Act: -0.0002

Data Index: 1480191 (Python Code)

Max Activating Token Index: 445

Text #1

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0961. Min Act: -0.0002

Data Index: 610409 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0960. Min Act: -0.0002

Data Index: 283698 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1345332 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0969. Min Act: -0.0002

Data Index: 882343 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1039. Min Act: -0.0002

Data Index: 572124 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1062832 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0849. Min Act: -0.0002

Data Index: 47189 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1582462 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1600727 (Python Code)

Max Activating Token Index: 407

Text #10

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1430123 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1375290 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1509666 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1522054 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1617942 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1002451 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1571790 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1541042 (Python Code)

Max Activating Token Index: 153

Text #18

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1587439 (Python Code)

Max Activating Token Index: 257

Text #19

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1637331 (Python Code)

Max Activating Token Index: 139