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

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

Neuron 4911 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: 0.8498. Min Range: -0.8498

Max Act: 0.8498. Min Act: -0.0002

Data Index: 1345726 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.8120. Min Act: -0.0002

Data Index: 1151581 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.8001. Min Act: -0.0002

Data Index: 126871 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.8008. Min Act: -0.0002

Data Index: 1299694 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7914. Min Act: -0.0002

Data Index: 887344 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7845. Min Act: -0.0002

Data Index: 1114194 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7742. Min Act: -0.0002

Data Index: 852105 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7828. Min Act: -0.0002

Data Index: 1173326 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7538. Min Act: -0.0002

Data Index: 1264311 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7538. Min Act: -0.0002

Data Index: 585622 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7589. Min Act: -0.0002

Data Index: 205142 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7654. Min Act: -0.0002

Data Index: 802347 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7515. Min Act: -0.0002

Data Index: 1171572 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7701. Min Act: -0.0002

Data Index: 86949 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7750. Min Act: -0.0002

Data Index: 2343 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7573. Min Act: -0.0002

Data Index: 742110 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7522. Min Act: -0.0002

Data Index: 605838 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7538. Min Act: -0.0002

Data Index: 491686 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7519. Min Act: -0.0002

Data Index: 1129168 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7456. Min Act: -0.0002

Data Index: 1249468 (C4 (Web Text))

Max Activating Token Index: 21