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

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

Neuron 5973 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.0656. Min Range: -3.0656

Max Act: 3.0656. Min Act: -0.0002

Data Index: 1232047 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 3.0656. Min Range: -3.0656

Max Act: 3.0228. Min Act: -0.0002

Data Index: 594756 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.7649. Min Act: -0.0002

Data Index: 1045725 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.7528. Min Act: -0.0002

Data Index: 871027 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.6780. Min Act: -0.0002

Data Index: 656441 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.6486. Min Act: -0.0002

Data Index: 127775 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.6205. Min Act: -0.0002

Data Index: 1148607 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.5865. Min Act: -0.0002

Data Index: 1102456 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.6189. Min Act: -0.0002

Data Index: 896758 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.5441. Min Act: -0.0002

Data Index: 910065 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.5466. Min Act: -0.0002

Data Index: 948272 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.5106. Min Act: -0.0002

Data Index: 929260 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.4980. Min Act: -0.0002

Data Index: 12921 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.5001. Min Act: -0.0002

Data Index: 1300618 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.5092. Min Act: -0.0002

Data Index: 560087 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.5044. Min Act: -0.0002

Data Index: 199242 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.4506. Min Act: -0.0002

Data Index: 108603 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.5705. Min Act: -0.0002

Data Index: 459130 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.4785. Min Act: -0.0002

Data Index: 627078 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.5138. Min Act: -0.0002

Data Index: 1159192 (C4 (Web Text))

Max Activating Token Index: 69