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

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

Neuron 220 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: 0.7251. Min Range: -0.7251

Max Act: 0.7251. Min Act: -0.0000

Data Index: 540584 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6230. Min Act: -0.0001

Data Index: 1437365 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6425. Min Act: -0.0001

Data Index: 1430476 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6474. Min Act: -0.0001

Data Index: 1379096 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6126. Min Act: -0.0001

Data Index: 1360598 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5535. Min Act: -0.0001

Data Index: 949300 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5635. Min Act: -0.0000

Data Index: 827015 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4781. Min Act: -0.0000

Data Index: 867339 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1188929 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4493. Min Act: -0.0001

Data Index: 1586610 (Python Code)

Max Activating Token Index: 185

Text #10

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4766. Min Act: -0.0001

Data Index: 1554124 (Python Code)

Max Activating Token Index: 628

Text #11

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4683. Min Act: -0.0001

Data Index: 473787 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4371. Min Act: -0.0001

Data Index: 1060230 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4246. Min Act: -0.0000

Data Index: 930205 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4507. Min Act: -0.0001

Data Index: 1211244 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4228. Min Act: -0.0000

Data Index: 320741 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4228. Min Act: -0.0001

Data Index: 917634 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4338. Min Act: -0.0000

Data Index: 240552 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4189. Min Act: -0.0000

Data Index: 302108 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4436. Min Act: -0.0001

Data Index: 1141415 (C4 (Web Text))

Max Activating Token Index: 692