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

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

Neuron 5797 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: 0.8057. Min Range: -0.8057

Max Act: 0.8057. Min Act: -0.0000

Data Index: 118021 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6396. Min Act: -0.0000

Data Index: 516734 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5860. Min Act: -0.0000

Data Index: 427231 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5589. Min Act: 0.0000

Data Index: 1246380 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1056637 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5054. Min Act: -0.0000

Data Index: 413424 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4539. Min Act: -0.0000

Data Index: 251931 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1363241 (Python Code)

Max Activating Token Index: 977

Text #8

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1102928 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1628569 (Python Code)

Max Activating Token Index: 334

Text #10

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4277. Min Act: 0.0000

Data Index: 1330616 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1468563 (Python Code)

Max Activating Token Index: 515

Text #12

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4150. Min Act: -0.0000

Data Index: 520427 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1439136 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4312. Min Act: -0.0000

Data Index: 305222 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4146. Min Act: -0.0000

Data Index: 397835 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4107. Min Act: -0.0000

Data Index: 923506 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1080480 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.3929. Min Act: -0.0000

Data Index: 233356 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1520015 (Python Code)

Max Activating Token Index: 790