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

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

Neuron 1781 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.2297. Min Act: -0.0000

Data Index: 857132 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.3035. Min Act: -0.0000

Data Index: 955286 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.1778. Min Act: -0.0000

Data Index: 1203172 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.2841. Min Act: -0.0000

Data Index: 980825 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.0549. Min Act: -0.0000

Data Index: 1040646 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.1064. Min Act: -0.0000

Data Index: 279734 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.0910. Min Act: -0.0000

Data Index: 688800 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.2028. Min Act: -0.0000

Data Index: 1110727 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.0549. Min Act: -0.0000

Data Index: 86875 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.1724. Min Act: -0.0000

Data Index: 692883 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.1384. Min Act: -0.0000

Data Index: 897276 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 2.3035. Min Range: -2.3035

Max Act: 1.8918. Min Act: -0.0000

Data Index: 1203463 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.1121. Min Act: -0.0000

Data Index: 78073 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.0788. Min Act: -0.0000

Data Index: 481471 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 2.3035. Min Range: -2.3035

Max Act: 1.9699. Min Act: -0.0000

Data Index: 706204 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.0578. Min Act: -0.0000

Data Index: 1165886 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 2.3035. Min Range: -2.3035

Max Act: 1.9197. Min Act: -0.0000

Data Index: 1080687 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 2.3035. Min Range: -2.3035

Max Act: 2.0307. Min Act: -0.0000

Data Index: 417003 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 2.3035. Min Range: -2.3035

Max Act: 1.9346. Min Act: -0.0000

Data Index: 352380 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 2.3035. Min Range: -2.3035

Max Act: 1.9227. Min Act: -0.0000

Data Index: 1115187 (C4 (Web Text))

Max Activating Token Index: 558