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

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

Neuron 4580 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4834. Min Range: -5.4834

Max Act: 5.4834. Min Act: -0.0000

Data Index: 979345 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 5.4834. Min Range: -5.4834

Max Act: 4.9345. Min Act: -0.0000

Data Index: 1354470 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 5.4834. Min Range: -5.4834

Max Act: 4.6702. Min Act: -0.0000

Data Index: 1171702 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 5.4834. Min Range: -5.4834

Max Act: 4.6302. Min Act: -0.0000

Data Index: 1276614 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 5.4834. Min Range: -5.4834

Max Act: 4.7576. Min Act: -0.0000

Data Index: 21174 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 5.4834. Min Range: -5.4834

Max Act: 4.6774. Min Act: -0.0000

Data Index: 1075506 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 5.4834. Min Range: -5.4834

Max Act: 4.6764. Min Act: -0.0000

Data Index: 790044 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.9412. Min Act: -0.0000

Data Index: 735624 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 5.4834. Min Range: -5.4834

Max Act: 4.0878. Min Act: -0.0000

Data Index: 657670 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.5821. Min Act: -0.0000

Data Index: 1352126 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.8363. Min Act: -0.0000

Data Index: 999738 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.9607. Min Act: -0.0000

Data Index: 224526 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.7321. Min Act: -0.0000

Data Index: 4268 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.9043. Min Act: -0.0000

Data Index: 659887 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.5807. Min Act: -0.0000

Data Index: 155016 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.6842. Min Act: -0.0000

Data Index: 1078157 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.6719. Min Act: -0.0000

Data Index: 1049675 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.6422. Min Act: -0.0000

Data Index: 989511 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.4429. Min Act: -0.0000

Data Index: 1308288 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 5.4834. Min Range: -5.4834

Max Act: 3.6223. Min Act: -0.0000

Data Index: 1259243 (C4 (Web Text))

Max Activating Token Index: 216