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

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

Neuron 4018 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4710. Min Act: -0.0001

Data Index: 585596 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4376. Min Act: -0.0001

Data Index: 810243 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4208. Min Act: -0.0001

Data Index: 237684 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4052. Min Act: -0.0001

Data Index: 253377 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4123. Min Act: -0.0001

Data Index: 52835 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3859. Min Act: -0.0001

Data Index: 546863 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3942. Min Act: -0.0001

Data Index: 257700 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3992. Min Act: -0.0001

Data Index: 102232 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3884. Min Act: -0.0001

Data Index: 156041 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3715. Min Act: -0.0001

Data Index: 894290 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3927. Min Act: -0.0001

Data Index: 822426 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3539. Min Act: -0.0001

Data Index: 956305 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3642. Min Act: -0.0001

Data Index: 383431 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3724. Min Act: -0.0001

Data Index: 734611 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3725. Min Act: -0.0001

Data Index: 1270506 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3678. Min Act: -0.0001

Data Index: 739951 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3667. Min Act: -0.0001

Data Index: 479960 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3692. Min Act: -0.0001

Data Index: 586416 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3659. Min Act: -0.0001

Data Index: 549969 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3662. Min Act: -0.0001

Data Index: 1194894 (C4 (Web Text))

Max Activating Token Index: 63