Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2264 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9968. Min Act: -0.0001

Data Index: 830106 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9740. Min Act: -0.0000

Data Index: 775415 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1311334 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1311571 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8923. Min Act: -0.0001

Data Index: 1127398 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8648. Min Act: -0.0001

Data Index: 1233738 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8745. Min Act: -0.0001

Data Index: 521850 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8147. Min Act: -0.0001

Data Index: 508353 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8706. Min Act: -0.0001

Data Index: 311748 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7348. Min Act: -0.0001

Data Index: 6578 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8873. Min Act: -0.0001

Data Index: 728705 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1332498 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8508. Min Act: -0.0000

Data Index: 291587 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8109. Min Act: -0.0001

Data Index: 33827 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7243. Min Act: -0.0001

Data Index: 115122 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1057806 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7899. Min Act: -0.0001

Data Index: 341596 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7822. Min Act: -0.0000

Data Index: 579803 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7001. Min Act: -0.0001

Data Index: 476505 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1192048 (C4 (Web Text))

Max Activating Token Index: 78