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

Dataset: The Pile

Neuron 1077 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1635429 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1363617 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1396094 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1213119 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0755. Min Act: -0.0000

Data Index: 73843 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1074044 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1501143 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0961. Min Act: -0.0000

Data Index: 723503 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1387917 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0250. Min Act: -0.0000

Data Index: 980175 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0488. Min Act: -0.0000

Data Index: 1399657 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0388. Min Act: -0.0000

Data Index: 133060 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0554. Min Act: -0.0000

Data Index: 738221 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0865. Min Act: -0.0000

Data Index: 725562 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0180. Min Act: -0.0000

Data Index: 306392 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0114. Min Act: -0.0000

Data Index: 287522 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1306103 (The Pile)

Max Activating Token Index: 401

Text #17

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9663. Min Act: -0.0000

Data Index: 536241 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9450. Min Act: -0.0000

Data Index: 239851 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 1.1011. Min Range: -1.1011

Max Act: 1.0048. Min Act: -0.0000

Data Index: 578431 (The Pile)

Max Activating Token Index: 587