Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.8772. Min Act: -0.0001

Data Index: 1112466 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.9940. Min Act: -0.0001

Data Index: 244507 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 3.0766. Min Range: -3.0766

Max Act: 3.0766. Min Act: -0.0000

Data Index: 1013034 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.4748. Min Act: -0.0000

Data Index: 336837 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.4398. Min Act: -0.0001

Data Index: 1277754 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.4357. Min Act: -0.0000

Data Index: 273948 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.3961. Min Act: -0.0001

Data Index: 394985 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.3140. Min Act: -0.0001

Data Index: 176453 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.0827. Min Act: -0.0000

Data Index: 335130 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.0613. Min Act: -0.0000

Data Index: 1131703 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.0483. Min Act: -0.0001

Data Index: 259897 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.1254. Min Act: -0.0001

Data Index: 1213011 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 3.0766. Min Range: -3.0766

Max Act: 1.9780. Min Act: -0.0001

Data Index: 1053822 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.0778. Min Act: -0.0000

Data Index: 740549 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.0585. Min Act: -0.0001

Data Index: 931126 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.0568. Min Act: -0.0001

Data Index: 136702 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 3.0766. Min Range: -3.0766

Max Act: 2.1408. Min Act: -0.0001

Data Index: 119715 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 3.0766. Min Range: -3.0766

Max Act: 1.7128. Min Act: -0.0000

Data Index: 392667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.0766. Min Range: -3.0766

Max Act: 1.9844. Min Act: -0.0001

Data Index: 1120253 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 3.0766. Min Range: -3.0766

Max Act: 1.9665. Min Act: -0.0001

Data Index: 212885 (C4 (Web Text))

Max Activating Token Index: 69