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

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

Neuron 3540 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: 1.1017. Min Range: -1.1017

Max Act: 1.1017. Min Act: -0.0000

Data Index: 936453 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.1017. Min Range: -1.1017

Max Act: 1.0857. Min Act: -0.0000

Data Index: 893392 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 1.1017. Min Range: -1.1017

Max Act: 1.0059. Min Act: -0.0000

Data Index: 905115 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.1017. Min Range: -1.1017

Max Act: 1.0004. Min Act: -0.0000

Data Index: 470235 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.9905. Min Act: -0.0000

Data Index: 51768 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1106568 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1081292 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8612. Min Act: -0.0000

Data Index: 690930 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8682. Min Act: -0.0000

Data Index: 291274 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1329620 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.9184. Min Act: -0.0000

Data Index: 404010 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8999. Min Act: -0.0000

Data Index: 141581 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8395. Min Act: -0.0000

Data Index: 44915 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8245. Min Act: -0.0000

Data Index: 173170 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8177. Min Act: -0.0000

Data Index: 50244 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8145. Min Act: -0.0000

Data Index: 360328 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8142. Min Act: -0.0000

Data Index: 512950 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.7627. Min Act: -0.0000

Data Index: 730288 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1289887 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1282488 (C4 (Web Text))

Max Activating Token Index: 207