Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3781. Min Range: -4.3781

Max Act: 4.3781. Min Act: -0.0001

Data Index: 1255543 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 4.3781. Min Range: -4.3781

Max Act: 4.1033. Min Act: -0.0001

Data Index: 259881 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 4.3781. Min Range: -4.3781

Max Act: 4.1130. Min Act: -0.0001

Data Index: 1242655 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.7440. Min Act: -0.0000

Data Index: 146396 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.5908. Min Act: -0.0001

Data Index: 309567 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.6893. Min Act: -0.0001

Data Index: 1017579 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.3320. Min Act: -0.0001

Data Index: 1337315 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.2374. Min Act: -0.0000

Data Index: 1090762 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.6254. Min Act: -0.0001

Data Index: 148139 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.5826. Min Act: -0.0001

Data Index: 333544 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.7377. Min Act: -0.0001

Data Index: 799809 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.0901. Min Act: -0.0000

Data Index: 865973 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.5492. Min Act: -0.0000

Data Index: 589281 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.5177. Min Act: -0.0001

Data Index: 1058934 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.5049. Min Act: -0.0001

Data Index: 887145 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.3382. Min Act: -0.0000

Data Index: 1083985 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.6342. Min Act: -0.0001

Data Index: 97712 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.0405. Min Act: -0.0001

Data Index: 59930 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.1577. Min Act: -0.0001

Data Index: 544859 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 4.3781. Min Range: -4.3781

Max Act: 3.2510. Min Act: -0.0001

Data Index: 632625 (C4 (Web Text))

Max Activating Token Index: 695