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

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

Neuron 869 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: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0001

Data Index: 133056 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0110. Min Act: -0.0001

Data Index: 171858 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0110. Min Act: -0.0001

Data Index: 467278 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 241074 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 565703 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0002

Data Index: 412930 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 268258 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 358832 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 196717 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 527025 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 78362 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 184502 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 161816 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 91233 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 244457 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 471217 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 27142 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 151590 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 444687 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0001

Data Index: 169285 (C4 (Web Text))

Max Activating Token Index: 1