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

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

Neuron 2682 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0988. Min Act: -0.0001

Data Index: 810285 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1274645 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1093728 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0905. Min Act: -0.0001

Data Index: 268630 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0810. Min Act: -0.0002

Data Index: 362616 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0859. Min Act: -0.0002

Data Index: 775313 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1128657 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0790. Min Act: -0.0001

Data Index: 525334 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0782. Min Act: -0.0002

Data Index: 276108 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0753. Min Act: -0.0002

Data Index: 750554 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1227007 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0727. Min Act: -0.0002

Data Index: 486804 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0735. Min Act: -0.0002

Data Index: 260474 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0783. Min Act: -0.0002

Data Index: 423011 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0752. Min Act: -0.0002

Data Index: 101290 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1070923 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1238133 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0747. Min Act: -0.0002

Data Index: 712921 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0713. Min Act: -0.0002

Data Index: 219211 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1308636 (C4 (Web Text))

Max Activating Token Index: 939