Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6084 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.2595. Min Range: -7.2595

Max Act: 7.0605. Min Act: -0.0000

Data Index: 532329 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 7.2595. Min Range: -7.2595

Max Act: 7.2595. Min Act: -0.0000

Data Index: 395234 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 7.2595. Min Range: -7.2595

Max Act: 6.6873. Min Act: -0.0001

Data Index: 1122587 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.9241. Min Act: -0.0000

Data Index: 211235 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.9430. Min Act: -0.0000

Data Index: 19970 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 7.2595. Min Range: -7.2595

Max Act: 6.0775. Min Act: -0.0000

Data Index: 648428 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.6378. Min Act: -0.0000

Data Index: 782099 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.8819. Min Act: -0.0000

Data Index: 1309427 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.8371. Min Act: -0.0000

Data Index: 37851 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 7.2595. Min Range: -7.2595

Max Act: 6.0131. Min Act: -0.0000

Data Index: 257796 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.7823. Min Act: -0.0000

Data Index: 567488 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.1415. Min Act: -0.0000

Data Index: 165083 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.5352. Min Act: -0.0000

Data Index: 668781 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 7.2595. Min Range: -7.2595

Max Act: 4.4665. Min Act: -0.0000

Data Index: 385742 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 7.2595. Min Range: -7.2595

Max Act: 6.1661. Min Act: -0.0000

Data Index: 490720 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.4434. Min Act: -0.0000

Data Index: 371041 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.7330. Min Act: -0.0000

Data Index: 888909 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 7.2595. Min Range: -7.2595

Max Act: 4.7582. Min Act: -0.0000

Data Index: 1028246 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.0181. Min Act: -0.0000

Data Index: 840469 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 7.2595. Min Range: -7.2595

Max Act: 5.3932. Min Act: -0.0000

Data Index: 789314 (C4 (Web Text))

Max Activating Token Index: 351