Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3530 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.1132. Min Act: -0.0000

Data Index: 861673 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1139261 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0851. Min Act: -0.0000

Data Index: 540967 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1105963 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0847. Min Act: -0.0000

Data Index: 965344 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0790. Min Act: -0.0000

Data Index: 568282 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0828. Min Act: -0.0000

Data Index: 536399 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0860. Min Act: -0.0000

Data Index: 262074 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0746. Min Act: -0.0000

Data Index: 266890 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1338985 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0825. Min Act: -0.0000

Data Index: 272931 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0826. Min Act: -0.0000

Data Index: 453146 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1190805 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0701. Min Act: 0.0000

Data Index: 228122 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1358594 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0751. Min Act: -0.0000

Data Index: 611028 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0740. Min Act: -0.0000

Data Index: 383367 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0730. Min Act: -0.0000

Data Index: 27311 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0714. Min Act: -0.0000

Data Index: 827991 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0682. Min Act: -0.0000

Data Index: 396499 (C4 (Web Text))

Max Activating Token Index: 675