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

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

Neuron 4103 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: 3.2031. Min Range: -3.2031

Max Act: 3.2031. Min Act: -0.0000

Data Index: 889566 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 3.2031. Min Range: -3.2031

Max Act: 3.0400. Min Act: -0.0000

Data Index: 1501086 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 3.2031. Min Range: -3.2031

Max Act: 3.1463. Min Act: -0.0000

Data Index: 1606744 (Python Code)

Max Activating Token Index: 527

Text #3

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.9780. Min Act: -0.0000

Data Index: 1138737 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.8549. Min Act: -0.0000

Data Index: 1349123 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.6618. Min Act: -0.0000

Data Index: 1330881 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.5484. Min Act: -0.0000

Data Index: 199544 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.4736. Min Act: -0.0000

Data Index: 498789 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.3551. Min Act: -0.0000

Data Index: 379675 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.3197. Min Act: -0.0000

Data Index: 502686 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.3053. Min Act: -0.0000

Data Index: 862047 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.1604. Min Act: -0.0000

Data Index: 21580 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.1458. Min Act: -0.0000

Data Index: 1276922 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.1451. Min Act: -0.0000

Data Index: 649958 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.3578. Min Act: -0.0000

Data Index: 904490 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.3699. Min Act: -0.0000

Data Index: 1280734 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.2382. Min Act: -0.0000

Data Index: 687034 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.2169. Min Act: -0.0000

Data Index: 675196 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.2157. Min Act: -0.0000

Data Index: 1285271 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 3.2031. Min Range: -3.2031

Max Act: 2.2060. Min Act: -0.0000

Data Index: 1638796 (Python Code)

Max Activating Token Index: 997