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

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

Neuron 2036 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7758. Min Act: -0.0000

Data Index: 447634 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7318. Min Act: -0.0000

Data Index: 217528 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1040982 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6948. Min Act: -0.0000

Data Index: 364749 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7078. Min Act: -0.0000

Data Index: 26959 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6885. Min Act: -0.0000

Data Index: 363496 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6572. Min Act: -0.0000

Data Index: 778017 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6340. Min Act: -0.0000

Data Index: 449078 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1036060 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6441. Min Act: -0.0000

Data Index: 150323 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7744. Min Act: -0.0000

Data Index: 548416 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1116664 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6604. Min Act: -0.0000

Data Index: 112890 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6110. Min Act: -0.0000

Data Index: 724967 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6565. Min Act: -0.0000

Data Index: 266234 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1205731 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6819. Min Act: -0.0000

Data Index: 96238 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6211. Min Act: -0.0000

Data Index: 440791 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6954. Min Act: -0.0000

Data Index: 748809 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1205053 (C4 (Web Text))

Max Activating Token Index: 7