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

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

Neuron 2664 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1227. Min Act: -0.0000

Data Index: 994016 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1115. Min Act: -0.0000

Data Index: 19487 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0879. Min Act: -0.0000

Data Index: 501953 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0817. Min Act: -0.0000

Data Index: 965190 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0826. Min Act: -0.0000

Data Index: 443075 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0828. Min Act: -0.0000

Data Index: 202644 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0795. Min Act: -0.0000

Data Index: 945627 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1276149 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0794. Min Act: -0.0000

Data Index: 387822 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1300515 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0740. Min Act: -0.0000

Data Index: 993267 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1343308 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1004383 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0706. Min Act: -0.0000

Data Index: 979295 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1158067 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0721. Min Act: -0.0000

Data Index: 333623 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0719. Min Act: -0.0000

Data Index: 922031 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0717. Min Act: -0.0000

Data Index: 438587 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0699. Min Act: -0.0000

Data Index: 860061 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1156833 (C4 (Web Text))

Max Activating Token Index: 937