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

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

Neuron 317 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.7920. Min Act: -0.0000

Data Index: 959179 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.9391. Min Act: -0.0000

Data Index: 911517 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.8270. Min Act: -0.0000

Data Index: 1148322 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.4272. Min Act: -0.0000

Data Index: 727971 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.1884. Min Act: -0.0000

Data Index: 323385 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.2956. Min Act: -0.0000

Data Index: 1119656 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.3078. Min Act: -0.0000

Data Index: 340549 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.2826. Min Act: -0.0000

Data Index: 253731 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.2397. Min Act: -0.0000

Data Index: 1294670 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1333166 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.1943. Min Act: -0.0000

Data Index: 366422 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.1866. Min Act: -0.0000

Data Index: 205944 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1222837 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.0945. Min Act: -0.0000

Data Index: 963925 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.1629. Min Act: -0.0000

Data Index: 782590 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.1449. Min Act: -0.0000

Data Index: 988619 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.1353. Min Act: -0.0000

Data Index: 138078 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.1229. Min Act: -0.0000

Data Index: 496336 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1072692 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 1.9391. Min Range: -1.9391

Max Act: 1.1378. Min Act: -0.0000

Data Index: 960507 (C4 (Web Text))

Max Activating Token Index: 604