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

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

Neuron 445 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1197. Min Act: -0.0002

Data Index: 494151 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1161. Min Act: -0.0002

Data Index: 111714 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0878. Min Act: -0.0002

Data Index: 46864 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0859. Min Act: -0.0002

Data Index: 933495 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0897. Min Act: -0.0002

Data Index: 444362 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0844. Min Act: -0.0002

Data Index: 526481 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0839. Min Act: -0.0002

Data Index: 230314 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1075540 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0886. Min Act: -0.0002

Data Index: 453282 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1152055 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1132523 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0820. Min Act: -0.0002

Data Index: 362078 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0794. Min Act: -0.0002

Data Index: 240995 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0786. Min Act: -0.0002

Data Index: 53879 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0783. Min Act: -0.0002

Data Index: 543152 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0811. Min Act: -0.0002

Data Index: 753010 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0721. Min Act: -0.0002

Data Index: 611603 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0859. Min Act: -0.0002

Data Index: 442478 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1258408 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0696. Min Act: -0.0002

Data Index: 723961 (C4 (Web Text))

Max Activating Token Index: 139