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

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

Neuron 2788 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4712. Min Range: -2.4712

Max Act: 2.4712. Min Act: -0.0000

Data Index: 844333 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 2.4712. Min Range: -2.4712

Max Act: 2.2545. Min Act: -0.0000

Data Index: 539764 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.8393. Min Act: -0.0000

Data Index: 1133324 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 2.4712. Min Range: -2.4712

Max Act: 2.0686. Min Act: -0.0000

Data Index: 644575 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 2.4712. Min Range: -2.4712

Max Act: 2.0579. Min Act: -0.0000

Data Index: 985131 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.8968. Min Act: -0.0000

Data Index: 801361 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.8825. Min Act: -0.0000

Data Index: 592807 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.8174. Min Act: -0.0000

Data Index: 225743 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.7295. Min Act: -0.0000

Data Index: 283140 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.9284. Min Act: -0.0000

Data Index: 364785 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.4645. Min Act: -0.0000

Data Index: 329986 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.5712. Min Act: -0.0000

Data Index: 244998 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.5460. Min Act: -0.0000

Data Index: 1288366 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.8298. Min Act: -0.0000

Data Index: 910187 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.5053. Min Act: -0.0000

Data Index: 245112 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.5788. Min Act: -0.0000

Data Index: 753844 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1073847 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.5878. Min Act: -0.0000

Data Index: 460503 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.4794. Min Act: -0.0000

Data Index: 486178 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 2.4712. Min Range: -2.4712

Max Act: 1.5501. Min Act: -0.0000

Data Index: 752364 (C4 (Web Text))

Max Activating Token Index: 424