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

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

Neuron 456 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: 2.1491. Min Range: -2.1491

Max Act: 2.1491. Min Act: -0.0000

Data Index: 1080295 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 2.1491. Min Range: -2.1491

Max Act: 2.0593. Min Act: -0.0000

Data Index: 266020 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 2.1491. Min Range: -2.1491

Max Act: 2.1477. Min Act: -0.0000

Data Index: 571544 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1037598 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.7759. Min Act: -0.0000

Data Index: 516674 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.6655. Min Act: -0.0000

Data Index: 1536345 (Python Code)

Max Activating Token Index: 393

Text #6

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.6410. Min Act: -0.0000

Data Index: 1233835 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.5798. Min Act: -0.0000

Data Index: 885912 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.7455. Min Act: -0.0000

Data Index: 1103113 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.4809. Min Act: -0.0000

Data Index: 476302 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.6461. Min Act: -0.0000

Data Index: 448287 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.5481. Min Act: -0.0000

Data Index: 976119 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.5532. Min Act: -0.0000

Data Index: 527825 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.4570. Min Act: -0.0000

Data Index: 110617 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1084622 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.5221. Min Act: -0.0000

Data Index: 374148 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1090670 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1164838 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.5952. Min Act: -0.0000

Data Index: 1275291 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 2.1491. Min Range: -2.1491

Max Act: 1.5791. Min Act: -0.0000

Data Index: 1057569 (C4 (Web Text))

Max Activating Token Index: 782