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

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

Neuron 2841 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: 0.5767. Min Range: -0.5767

Max Act: 0.5767. Min Act: -0.0000

Data Index: 107265 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5158. Min Act: -0.0000

Data Index: 747894 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4938. Min Act: -0.0000

Data Index: 430200 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4999. Min Act: -0.0000

Data Index: 205093 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1125392 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4329. Min Act: -0.0000

Data Index: 289587 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1004373 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4732. Min Act: -0.0000

Data Index: 94678 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1326169 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4473. Min Act: -0.0000

Data Index: 973317 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4192. Min Act: -0.0000

Data Index: 883186 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4059. Min Act: -0.0000

Data Index: 43079 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1633914 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1585269 (Python Code)

Max Activating Token Index: 865

Text #14

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3868. Min Act: -0.0000

Data Index: 933735 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4024. Min Act: -0.0000

Data Index: 924503 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3839. Min Act: -0.0000

Data Index: 25968 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3843. Min Act: -0.0000

Data Index: 403294 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3819. Min Act: -0.0000

Data Index: 871562 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3757. Min Act: -0.0000

Data Index: 662697 (C4 (Web Text))

Max Activating Token Index: 648