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

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

Neuron 1682 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.3441. Min Act: -0.0000

Data Index: 382534 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.3285. Min Act: -0.0000

Data Index: 918790 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.2666. Min Act: -0.0000

Data Index: 957676 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.3067. Min Act: -0.0000

Data Index: 589683 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.1309. Min Act: -0.0000

Data Index: 2063 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0680. Min Act: -0.0000

Data Index: 268354 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1316943 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1021692 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0889. Min Act: -0.0000

Data Index: 12835 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0778. Min Act: -0.0000

Data Index: 656804 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.1109. Min Act: -0.0000

Data Index: 713582 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0785. Min Act: -0.0000

Data Index: 746366 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1047418 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0144. Min Act: -0.0000

Data Index: 735364 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9766. Min Act: -0.0000

Data Index: 108335 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9990. Min Act: -0.0000

Data Index: 508177 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9692. Min Act: -0.0000

Data Index: 740300 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1090005 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1029034 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9878. Min Act: -0.0000

Data Index: 38611 (C4 (Web Text))

Max Activating Token Index: 636