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

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

Neuron 3093 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: 1.3683. Min Range: -1.3683

Max Act: 1.3683. Min Act: -0.0002

Data Index: 918899 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 1.3683. Min Range: -1.3683

Max Act: 1.3053. Min Act: -0.0001

Data Index: 1272717 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.3683. Min Range: -1.3683

Max Act: 1.0389. Min Act: -0.0002

Data Index: 868772 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.9873. Min Act: -0.0001

Data Index: 278662 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.9611. Min Act: -0.0001

Data Index: 353431 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.9052. Min Act: -0.0001

Data Index: 60144 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.9315. Min Act: -0.0002

Data Index: 498125 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.9430. Min Act: -0.0002

Data Index: 1134702 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.8565. Min Act: -0.0002

Data Index: 1267043 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.9074. Min Act: -0.0002

Data Index: 753154 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.9076. Min Act: -0.0001

Data Index: 697496 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.8351. Min Act: -0.0001

Data Index: 444318 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.8393. Min Act: -0.0002

Data Index: 1215187 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.8620. Min Act: -0.0002

Data Index: 614683 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.8449. Min Act: -0.0001

Data Index: 482990 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.8542. Min Act: -0.0002

Data Index: 701107 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.8243. Min Act: -0.0002

Data Index: 1146413 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.8152. Min Act: -0.0002

Data Index: 25961 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.3683. Min Range: -1.3683

Max Act: 0.8098. Min Act: -0.0002

Data Index: 886347 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 1.3683. Min Range: -1.3683

Max Act: 1.0295. Min Act: -0.0002

Data Index: 114956 (C4 (Web Text))

Max Activating Token Index: 634