Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 664 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6948. Min Act: -0.0001

Data Index: 553060 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6484. Min Act: -0.0001

Data Index: 1139290 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5751. Min Act: -0.0001

Data Index: 432168 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5970. Min Act: -0.0001

Data Index: 1025842 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5732. Min Act: -0.0001

Data Index: 1320929 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5942. Min Act: -0.0001

Data Index: 144946 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5764. Min Act: -0.0001

Data Index: 938024 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5381. Min Act: -0.0001

Data Index: 224565 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5859. Min Act: -0.0001

Data Index: 50762 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5642. Min Act: -0.0001

Data Index: 675011 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5260. Min Act: -0.0001

Data Index: 1496976 (Python Code)

Max Activating Token Index: 303

Text #11

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5782. Min Act: -0.0001

Data Index: 1274272 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5754. Min Act: -0.0001

Data Index: 551697 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5529. Min Act: -0.0001

Data Index: 917360 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5346. Min Act: -0.0001

Data Index: 217124 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5369. Min Act: -0.0001

Data Index: 922074 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5438. Min Act: -0.0001

Data Index: 189609 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5595. Min Act: -0.0001

Data Index: 453956 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5301. Min Act: -0.0001

Data Index: 688742 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5446. Min Act: -0.0001

Data Index: 156840 (C4 (Web Text))

Max Activating Token Index: 749