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

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

Neuron 2766 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: 3.7287. Min Range: -3.7287

Max Act: 3.7287. Min Act: -0.0000

Data Index: 890025 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 3.7287. Min Range: -3.7287

Max Act: 3.3875. Min Act: -0.0000

Data Index: 696993 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 3.7287. Min Range: -3.7287

Max Act: 3.2955. Min Act: -0.0000

Data Index: 385652 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 3.7287. Min Range: -3.7287

Max Act: 3.0643. Min Act: -0.0000

Data Index: 105142 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.7287. Min Range: -3.7287

Max Act: 3.0439. Min Act: -0.0000

Data Index: 912807 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 3.7287. Min Range: -3.7287

Max Act: 3.1688. Min Act: -0.0000

Data Index: 566189 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.7726. Min Act: -0.0001

Data Index: 104537 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 3.7287. Min Range: -3.7287

Max Act: 3.1072. Min Act: -0.0001

Data Index: 1137634 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.8359. Min Act: -0.0000

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.9482. Min Act: -0.0000

Data Index: 623453 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.8070. Min Act: -0.0000

Data Index: 165549 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.8515. Min Act: -0.0000

Data Index: 1304964 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.8272. Min Act: -0.0000

Data Index: 157869 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.8168. Min Act: -0.0000

Data Index: 518764 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.7381. Min Act: -0.0001

Data Index: 605128 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.6181. Min Act: -0.0000

Data Index: 1358794 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.5018. Min Act: -0.0000

Data Index: 698462 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.4631. Min Act: -0.0000

Data Index: 302986 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.5359. Min Act: -0.0001

Data Index: 322997 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 3.7287. Min Range: -3.7287

Max Act: 2.6294. Min Act: -0.0000

Data Index: 789919 (C4 (Web Text))

Max Activating Token Index: 584