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

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

Neuron 3379 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: 0.9054. Min Range: -0.9054

Max Act: 0.9054. Min Act: -0.0001

Data Index: 891927 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8998. Min Act: -0.0001

Data Index: 175132 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.9021. Min Act: -0.0001

Data Index: 1025893 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8807. Min Act: -0.0001

Data Index: 457831 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8673. Min Act: -0.0001

Data Index: 806008 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8828. Min Act: -0.0002

Data Index: 1249463 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8540. Min Act: -0.0001

Data Index: 320585 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8572. Min Act: -0.0001

Data Index: 503942 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8468. Min Act: -0.0001

Data Index: 360007 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8465. Min Act: -0.0001

Data Index: 549819 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8363. Min Act: -0.0001

Data Index: 1067633 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8395. Min Act: -0.0001

Data Index: 768299 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8264. Min Act: -0.0001

Data Index: 1088877 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8375. Min Act: -0.0001

Data Index: 1189771 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8335. Min Act: -0.0001

Data Index: 1262806 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8381. Min Act: -0.0001

Data Index: 872257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8175. Min Act: -0.0001

Data Index: 5880 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8147. Min Act: -0.0001

Data Index: 1341311 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8343. Min Act: -0.0001

Data Index: 967674 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8180. Min Act: -0.0001

Data Index: 1058013 (C4 (Web Text))

Max Activating Token Index: 27