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

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

Neuron 2646 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.3810. Min Act: -0.0000

Data Index: 279302 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1239276 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.1557. Min Act: -0.0000

Data Index: 825563 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.0582. Min Act: -0.0000

Data Index: 211741 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.0525. Min Act: -0.0000

Data Index: 104810 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1310629 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.9727. Min Act: -0.0000

Data Index: 985636 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 1.4309. Min Range: -1.4309

Max Act: 1.0305. Min Act: -0.0000

Data Index: 248787 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.9973. Min Act: -0.0000

Data Index: 892161 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8905. Min Act: -0.0000

Data Index: 410118 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.9021. Min Act: -0.0000

Data Index: 977368 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1331236 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8314. Min Act: -0.0000

Data Index: 936293 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8280. Min Act: -0.0000

Data Index: 58270 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8224. Min Act: -0.0000

Data Index: 586963 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.8779. Min Act: -0.0000

Data Index: 453239 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.7747. Min Act: -0.0000

Data Index: 384830 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.7796. Min Act: -0.0000

Data Index: 531976 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.7301. Min Act: -0.0000

Data Index: 203478 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.4309. Min Range: -1.4309

Max Act: 0.7500. Min Act: -0.0000

Data Index: 670256 (C4 (Web Text))

Max Activating Token Index: 22