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

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

Neuron 2372 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: 0.6789. Min Range: -0.6789

Max Act: 0.6789. Min Act: -0.0001

Data Index: 8785 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5420. Min Act: -0.0001

Data Index: 505491 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5815. Min Act: -0.0001

Data Index: 10390 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5890. Min Act: -0.0001

Data Index: 660199 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5211. Min Act: -0.0000

Data Index: 892404 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5294. Min Act: -0.0001

Data Index: 1211794 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5481. Min Act: -0.0001

Data Index: 999028 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4685. Min Act: -0.0001

Data Index: 895699 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4639. Min Act: -0.0001

Data Index: 239213 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4033. Min Act: -0.0000

Data Index: 314690 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4734. Min Act: -0.0000

Data Index: 406720 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4607. Min Act: -0.0000

Data Index: 957808 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4862. Min Act: -0.0001

Data Index: 301932 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4570. Min Act: -0.0000

Data Index: 958934 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4637. Min Act: -0.0000

Data Index: 54739 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4353. Min Act: -0.0000

Data Index: 276246 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4417. Min Act: -0.0001

Data Index: 767438 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4492. Min Act: -0.0000

Data Index: 389979 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1081317 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4117. Min Act: -0.0001

Data Index: 581264 (C4 (Web Text))

Max Activating Token Index: 292