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

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

Neuron 3575 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3256. Min Range: -6.3256

Max Act: 6.3256. Min Act: -0.0000

Data Index: 381325 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.9628. Min Act: -0.0000

Data Index: 821111 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 6.3256. Min Range: -6.3256

Max Act: 6.1453. Min Act: -0.0000

Data Index: 1322156 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.1137. Min Act: -0.0000

Data Index: 509591 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.3285. Min Act: -0.0000

Data Index: 1225571 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.3638. Min Act: -0.0000

Data Index: 410924 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 6.3256. Min Range: -6.3256

Max Act: 4.9317. Min Act: -0.0000

Data Index: 859979 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.1897. Min Act: -0.0000

Data Index: 961980 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.3554. Min Act: -0.0000

Data Index: 298832 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.2880. Min Act: -0.0000

Data Index: 27253 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 6.3256. Min Range: -6.3256

Max Act: 4.6200. Min Act: -0.0000

Data Index: 101545 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.4708. Min Act: -0.0000

Data Index: 435765 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.1484. Min Act: -0.0000

Data Index: 997813 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 6.3256. Min Range: -6.3256

Max Act: 4.9111. Min Act: -0.0000

Data Index: 602205 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 6.3256. Min Range: -6.3256

Max Act: 4.3734. Min Act: -0.0000

Data Index: 123488 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 6.3256. Min Range: -6.3256

Max Act: 4.4707. Min Act: -0.0000

Data Index: 760222 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 6.3256. Min Range: -6.3256

Max Act: 4.9884. Min Act: -0.0000

Data Index: 803531 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 6.3256. Min Range: -6.3256

Max Act: 4.7924. Min Act: -0.0000

Data Index: 988381 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 6.3256. Min Range: -6.3256

Max Act: 4.5550. Min Act: -0.0000

Data Index: 1281071 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 6.3256. Min Range: -6.3256

Max Act: 5.1533. Min Act: -0.0000

Data Index: 724994 (C4 (Web Text))

Max Activating Token Index: 546