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

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

Neuron 3137 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.9651. Min Act: -0.0002

Data Index: 1188317 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.9606. Min Act: -0.0002

Data Index: 622455 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.8207. Min Act: -0.0003

Data Index: 682519 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.6911. Min Act: -0.0002

Data Index: 384118 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.6750. Min Act: -0.0002

Data Index: 464098 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.5504. Min Act: -0.0002

Data Index: 1357860 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.6247. Min Act: -0.0002

Data Index: 985512 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.6680. Min Act: -0.0002

Data Index: 602344 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.5614. Min Act: -0.0002

Data Index: 50609 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.5277. Min Act: -0.0002

Data Index: 952458 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.5731. Min Act: -0.0002

Data Index: 951061 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.5717. Min Act: -0.0002

Data Index: 906177 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.4795. Min Act: -0.0002

Data Index: 111208 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.4723. Min Act: -0.0002

Data Index: 421891 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.4918. Min Act: -0.0002

Data Index: 946700 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.4832. Min Act: -0.0002

Data Index: 1043073 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.4382. Min Act: -0.0002

Data Index: 81637 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.3765. Min Act: -0.0002

Data Index: 933390 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.4039. Min Act: -0.0002

Data Index: 824689 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 2.9651. Min Range: -2.9651

Max Act: 2.3503. Min Act: -0.0002

Data Index: 338702 (C4 (Web Text))

Max Activating Token Index: 307