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

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

Neuron 2573 in Layer 1

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: 0.6594. Min Range: -0.6594

Max Act: 0.6574. Min Act: -0.0003

Data Index: 825841 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.6594. Min Act: -0.0002

Data Index: 606500 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.6176. Min Act: -0.0002

Data Index: 940817 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.6200. Min Act: -0.0003

Data Index: 1198770 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.6188. Min Act: -0.0003

Data Index: 534652 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.6087. Min Act: -0.0002

Data Index: 571912 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5970. Min Act: -0.0002

Data Index: 668281 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5892. Min Act: -0.0002

Data Index: 922047 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5963. Min Act: -0.0002

Data Index: 1161849 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5843. Min Act: -0.0002

Data Index: 1209140 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5940. Min Act: -0.0002

Data Index: 300380 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5766. Min Act: -0.0002

Data Index: 166056 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5850. Min Act: -0.0003

Data Index: 259761 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5841. Min Act: -0.0002

Data Index: 481136 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5731. Min Act: -0.0002

Data Index: 1303442 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5757. Min Act: -0.0003

Data Index: 876079 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5802. Min Act: -0.0002

Data Index: 1095845 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5682. Min Act: -0.0003

Data Index: 1008187 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5768. Min Act: -0.0002

Data Index: 1039583 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5622. Min Act: -0.0002

Data Index: 491354 (C4 (Web Text))

Max Activating Token Index: 95