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

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

Neuron 2156 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: 2.8621. Min Range: -2.8621

Max Act: 2.7901. Min Act: -0.0000

Data Index: 1202514 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.5148. Min Act: -0.0000

Data Index: 321328 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.6695. Min Act: -0.0000

Data Index: 180281 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.7066. Min Act: -0.0000

Data Index: 271050 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.4789. Min Act: -0.0000

Data Index: 865558 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.4757. Min Act: -0.0000

Data Index: 903685 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.8621. Min Act: -0.0001

Data Index: 1088639 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.5698. Min Act: -0.0000

Data Index: 798861 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.3423. Min Act: -0.0000

Data Index: 1046315 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.4587. Min Act: -0.0000

Data Index: 41486 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.5729. Min Act: -0.0000

Data Index: 68223 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.7460. Min Act: -0.0000

Data Index: 400537 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.2614. Min Act: -0.0000

Data Index: 57821 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.2822. Min Act: -0.0000

Data Index: 288169 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.3769. Min Act: -0.0000

Data Index: 644070 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.4986. Min Act: -0.0000

Data Index: 242997 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.3723. Min Act: -0.0000

Data Index: 991550 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.3543. Min Act: -0.0000

Data Index: 833541 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1213117 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 2.8621. Min Range: -2.8621

Max Act: 2.4563. Min Act: -0.0001

Data Index: 627040 (C4 (Web Text))

Max Activating Token Index: 944