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

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

Neuron 773 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1109332 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5618. Min Act: 0.0000

Data Index: 491088 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1234309 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5533. Min Act: -0.0000

Data Index: 270837 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5841. Min Act: 0.0000

Data Index: 632865 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5188. Min Act: -0.0000

Data Index: 368613 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5035. Min Act: -0.0000

Data Index: 412657 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4702. Min Act: -0.0000

Data Index: 234428 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4629. Min Act: -0.0000

Data Index: 258030 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4572. Min Act: -0.0000

Data Index: 388672 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1270119 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4527. Min Act: -0.0000

Data Index: 666869 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1654959 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1594062 (Python Code)

Max Activating Token Index: 504

Text #14

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4475. Min Act: -0.0000

Data Index: 879109 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1428111 (Python Code)

Max Activating Token Index: 547

Text #16

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4136. Min Act: 0.0000

Data Index: 484753 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1637245 (Python Code)

Max Activating Token Index: 801

Text #18

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1390127 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4001. Min Act: -0.0000

Data Index: 656055 (C4 (Web Text))

Max Activating Token Index: 368