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

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

Neuron 4215 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.7928. Min Act: -0.0000

Data Index: 940730 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6978. Min Act: -0.0000

Data Index: 675697 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.6491. Min Act: -0.0000

Data Index: 945540 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1295208 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.5324. Min Act: -0.0000

Data Index: 738023 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.5140. Min Act: -0.0000

Data Index: 734522 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4740. Min Act: -0.0000

Data Index: 809392 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.5041. Min Act: -0.0000

Data Index: 420889 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1079491 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4997. Min Act: -0.0000

Data Index: 166060 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1028362 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4902. Min Act: -0.0000

Data Index: 135523 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4683. Min Act: -0.0000

Data Index: 840333 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4833. Min Act: -0.0000

Data Index: 279161 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4767. Min Act: -0.0000

Data Index: 519446 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1095061 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4759. Min Act: -0.0000

Data Index: 151592 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4753. Min Act: -0.0000

Data Index: 92063 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4906. Min Act: -0.0000

Data Index: 237599 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.7928. Min Range: -0.7928

Max Act: 0.4844. Min Act: -0.0000

Data Index: 434346 (C4 (Web Text))

Max Activating Token Index: 987