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

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

Neuron 280 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: 0.4768. Min Range: -0.4768

Max Act: 0.4768. Min Act: -0.0001

Data Index: 874956 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3938. Min Act: -0.0000

Data Index: 610717 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3432. Min Act: -0.0000

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3628. Min Act: -0.0001

Data Index: 846398 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3527. Min Act: -0.0000

Data Index: 389181 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1274237 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1048929 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3327. Min Act: -0.0000

Data Index: 337160 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1010682 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3378. Min Act: -0.0000

Data Index: 349175 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1006650 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3115. Min Act: -0.0000

Data Index: 88799 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2982. Min Act: -0.0000

Data Index: 224383 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1019693 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1013322 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2637. Min Act: -0.0000

Data Index: 67986 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1067821 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2702. Min Act: -0.0000

Data Index: 139240 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2538. Min Act: -0.0000

Data Index: 985389 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2364. Min Act: -0.0001

Data Index: 664185 (C4 (Web Text))

Max Activating Token Index: 895