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

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

Neuron 600 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.5232. Min Act: -0.0000

Data Index: 412613 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4427. Min Act: -0.0000

Data Index: 848640 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1284156 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.4164. Min Act: -0.0000

Data Index: 584853 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3767. Min Act: -0.0000

Data Index: 751186 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3928. Min Act: -0.0000

Data Index: 442482 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1136732 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3714. Min Act: -0.0000

Data Index: 414998 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3624. Min Act: -0.0000

Data Index: 788789 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3598. Min Act: -0.0000

Data Index: 941396 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1248766 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3424. Min Act: -0.0000

Data Index: 644516 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3391. Min Act: -0.0000

Data Index: 455605 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3303. Min Act: -0.0000

Data Index: 526878 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1257407 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3276. Min Act: -0.0000

Data Index: 68689 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3456. Min Act: -0.0000

Data Index: 165326 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1019614 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3420. Min Act: -0.0000

Data Index: 553889 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.5232. Min Range: -0.5232

Max Act: 0.3292. Min Act: -0.0000

Data Index: 859716 (C4 (Web Text))

Max Activating Token Index: 195