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

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

Neuron 3174 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: 1.8693. Min Range: -1.8693

Max Act: 1.8693. Min Act: -0.0000

Data Index: 975210 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.7021. Min Act: -0.0000

Data Index: 1374456 (Python Code)

Max Activating Token Index: 453

Text #2

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.5398. Min Act: -0.0000

Data Index: 153283 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.4948. Min Act: -0.0000

Data Index: 15085 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.5800. Min Act: -0.0000

Data Index: 142059 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.6615. Min Act: -0.0000

Data Index: 1186685 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.4826. Min Act: -0.0000

Data Index: 63912 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1200513 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.5257. Min Act: -0.0000

Data Index: 316462 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.5146. Min Act: -0.0000

Data Index: 1041908 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.4834. Min Act: -0.0000

Data Index: 1108072 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.5581. Min Act: -0.0000

Data Index: 1529547 (Python Code)

Max Activating Token Index: 746

Text #12

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.3226. Min Act: -0.0000

Data Index: 224258 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.3970. Min Act: -0.0000

Data Index: 478187 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.3769. Min Act: -0.0000

Data Index: 211234 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.3091. Min Act: -0.0000

Data Index: 608654 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.3882. Min Act: -0.0000

Data Index: 543947 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.3571. Min Act: -0.0000

Data Index: 1306401 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.5290. Min Act: -0.0000

Data Index: 927193 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 1.8693. Min Range: -1.8693

Max Act: 1.2854. Min Act: -0.0000

Data Index: 1083960 (C4 (Web Text))

Max Activating Token Index: 6