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

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

Neuron 3364 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3781. Min Range: -5.3781

Max Act: 5.3781. Min Act: -0.0001

Data Index: 1148098 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 5.3781. Min Range: -5.3781

Max Act: 4.5437. Min Act: -0.0001

Data Index: 1215785 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 5.3781. Min Range: -5.3781

Max Act: 4.4233. Min Act: -0.0001

Data Index: 827495 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 5.3781. Min Range: -5.3781

Max Act: 4.4243. Min Act: -0.0001

Data Index: 839764 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 5.3781. Min Range: -5.3781

Max Act: 4.0102. Min Act: -0.0000

Data Index: 965501 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 5.3781. Min Range: -5.3781

Max Act: 4.1435. Min Act: -0.0001

Data Index: 906331 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 5.3781. Min Range: -5.3781

Max Act: 4.1109. Min Act: -0.0001

Data Index: 384692 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 5.3781. Min Range: -5.3781

Max Act: 4.0915. Min Act: -0.0000

Data Index: 972247 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.8553. Min Act: -0.0000

Data Index: 82140 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.8131. Min Act: -0.0001

Data Index: 162185 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.9521. Min Act: -0.0001

Data Index: 645025 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.9340. Min Act: -0.0001

Data Index: 1006754 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.9226. Min Act: -0.0001

Data Index: 5308 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.8969. Min Act: -0.0001

Data Index: 748708 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.8908. Min Act: -0.0001

Data Index: 208880 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.7401. Min Act: -0.0000

Data Index: 385129 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.8796. Min Act: -0.0000

Data Index: 807721 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.8341. Min Act: -0.0001

Data Index: 472828 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.7948. Min Act: -0.0000

Data Index: 1022921 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 5.3781. Min Range: -5.3781

Max Act: 3.7169. Min Act: -0.0001

Data Index: 1237859 (C4 (Web Text))

Max Activating Token Index: 53