Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 899 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5931. Min Act: -0.0004

Data Index: 1007630 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5884. Min Act: -0.0004

Data Index: 404564 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.6010. Min Act: -0.0004

Data Index: 656335 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5589. Min Act: -0.0004

Data Index: 225901 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4732. Min Act: -0.0004

Data Index: 677675 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4591. Min Act: -0.0004

Data Index: 215094 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4685. Min Act: -0.0004

Data Index: 1233905 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4834. Min Act: -0.0004

Data Index: 905536 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4913. Min Act: -0.0004

Data Index: 275993 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4894. Min Act: -0.0004

Data Index: 303419 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4549. Min Act: -0.0004

Data Index: 1065258 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4516. Min Act: -0.0004

Data Index: 336750 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4807. Min Act: -0.0004

Data Index: 111700 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4644. Min Act: -0.0004

Data Index: 729046 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4764. Min Act: -0.0004

Data Index: 306544 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4915. Min Act: -0.0004

Data Index: 234470 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4732. Min Act: -0.0004

Data Index: 566086 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4698. Min Act: -0.0004

Data Index: 1269713 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4417. Min Act: -0.0004

Data Index: 796221 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4538. Min Act: -0.0004

Data Index: 1097753 (C4 (Web Text))

Max Activating Token Index: 258