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

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

Neuron 847 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.9364. Min Act: 0.0000

Data Index: 1112692 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1156051 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1026082 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.7550. Min Act: -0.0000

Data Index: 98084 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.7019. Min Act: -0.0000

Data Index: 461005 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.7677. Min Act: -0.0000

Data Index: 961215 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.7373. Min Act: -0.0000

Data Index: 448835 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1275543 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1224258 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.6832. Min Act: -0.0000

Data Index: 166007 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.6539. Min Act: -0.0000

Data Index: 307987 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.6685. Min Act: -0.0000

Data Index: 423895 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.6328. Min Act: -0.0000

Data Index: 671540 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.6068. Min Act: -0.0000

Data Index: 370073 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.6082. Min Act: -0.0000

Data Index: 519366 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.6019. Min Act: -0.0000

Data Index: 865931 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.5797. Min Act: -0.0000

Data Index: 733088 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.5804. Min Act: -0.0000

Data Index: 670386 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1100061 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.9364. Min Range: -0.9364

Max Act: 0.5945. Min Act: 0.0000

Data Index: 1236589 (C4 (Web Text))

Max Activating Token Index: 619