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

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

Neuron 5756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1046743 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.4187. Min Act: -0.0000

Data Index: 151216 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2575. Min Act: -0.0000

Data Index: 689132 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.3536. Min Act: -0.0000

Data Index: 1140039 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1336600 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2509. Min Act: -0.0000

Data Index: 287164 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2488. Min Act: -0.0000

Data Index: 186224 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1193244 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.3265. Min Act: -0.0000

Data Index: 759171 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2060. Min Act: -0.0000

Data Index: 187429 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1990. Min Act: -0.0000

Data Index: 108410 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1508. Min Act: -0.0000

Data Index: 96022 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1520712 (Python Code)

Max Activating Token Index: 704

Text #13

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1961. Min Act: -0.0000

Data Index: 211801 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2181. Min Act: -0.0000

Data Index: 215703 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1387. Min Act: -0.0000

Data Index: 757403 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.2085. Min Act: -0.0000

Data Index: 285446 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1232091 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1890. Min Act: -0.0000

Data Index: 162267 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.4950. Min Range: -1.4950

Max Act: 1.1833. Min Act: -0.0000

Data Index: 416941 (C4 (Web Text))

Max Activating Token Index: 761