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

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

Neuron 1075 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1138. Min Act: -0.0001

Data Index: 374415 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1000. Min Act: -0.0001

Data Index: 504831 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0958. Min Act: -0.0001

Data Index: 220521 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1103168 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0903. Min Act: -0.0001

Data Index: 778570 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0858. Min Act: -0.0001

Data Index: 897683 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0866. Min Act: -0.0001

Data Index: 826727 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0824. Min Act: -0.0001

Data Index: 986710 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0793. Min Act: -0.0001

Data Index: 798235 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1016996 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0782. Min Act: -0.0001

Data Index: 604817 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0796. Min Act: -0.0001

Data Index: 176591 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1205517 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1123688 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1065893 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0731. Min Act: -0.0001

Data Index: 642555 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1555107 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0717. Min Act: -0.0001

Data Index: 177500 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0724. Min Act: -0.0001

Data Index: 898645 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0695. Min Act: -0.0001

Data Index: 47509 (C4 (Web Text))

Max Activating Token Index: 93