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

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

Neuron 4921 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1650. Min Range: -1.1650

Max Act: 1.1288. Min Act: -0.0000

Data Index: 603386 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 1.1650. Min Range: -1.1650

Max Act: 1.1191. Min Act: -0.0000

Data Index: 947754 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.1650. Min Range: -1.1650

Max Act: 1.1650. Min Act: -0.0000

Data Index: 586182 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.1650. Min Range: -1.1650

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1077451 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.9978. Min Act: -0.0000

Data Index: 777054 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.1650. Min Range: -1.1650

Max Act: 1.0021. Min Act: -0.0000

Data Index: 701048 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 1.1650. Min Range: -1.1650

Max Act: 1.0228. Min Act: -0.0000

Data Index: 241851 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.9517. Min Act: -0.0000

Data Index: 901350 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.9475. Min Act: -0.0001

Data Index: 874376 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.9095. Min Act: -0.0000

Data Index: 276779 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.9302. Min Act: -0.0000

Data Index: 845842 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1263580 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.8847. Min Act: -0.0000

Data Index: 612581 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1240263 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.8903. Min Act: -0.0000

Data Index: 404853 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1618457 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.8793. Min Act: -0.0000

Data Index: 502157 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1032285 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.8875. Min Act: -0.0000

Data Index: 263381 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.1650. Min Range: -1.1650

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1282170 (C4 (Web Text))

Max Activating Token Index: 893