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

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

Neuron 3241 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: 1.9701. Min Range: -1.9701

Max Act: 1.9701. Min Act: -0.0001

Data Index: 708440 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.8211. Min Act: -0.0000

Data Index: 865502 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.8764. Min Act: -0.0001

Data Index: 735475 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.9088. Min Act: -0.0001

Data Index: 945352 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.8208. Min Act: -0.0001

Data Index: 337983 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.6908. Min Act: -0.0000

Data Index: 234701 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5647. Min Act: -0.0001

Data Index: 116708 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5579. Min Act: -0.0001

Data Index: 681429 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.6130. Min Act: -0.0001

Data Index: 214246 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5548. Min Act: -0.0001

Data Index: 332912 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.6971. Min Act: -0.0001

Data Index: 1305744 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5604. Min Act: -0.0001

Data Index: 360909 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.4726. Min Act: -0.0001

Data Index: 893045 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.4671. Min Act: -0.0001

Data Index: 622148 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5045. Min Act: -0.0001

Data Index: 783988 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5333. Min Act: -0.0001

Data Index: 49325 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5367. Min Act: -0.0001

Data Index: 846795 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5340. Min Act: -0.0001

Data Index: 348496 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5340. Min Act: -0.0001

Data Index: 204886 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.9701. Min Range: -1.9701

Max Act: 1.5431. Min Act: -0.0001

Data Index: 919659 (C4 (Web Text))

Max Activating Token Index: 766