Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2339 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1246618 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1100563 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0840. Min Act: -0.0000

Data Index: 936199 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0333. Min Act: -0.0000

Data Index: 290506 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0576. Min Act: -0.0000

Data Index: 31648 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0290. Min Act: -0.0000

Data Index: 648486 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1184429 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1088849 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0246. Min Act: -0.0000

Data Index: 976276 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1204999 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1386192 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0346. Min Act: -0.0000

Data Index: 1560874 (Python Code)

Max Activating Token Index: 228

Text #12

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9635. Min Act: -0.0000

Data Index: 605246 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1400790 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9240. Min Act: -0.0000

Data Index: 499813 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9717. Min Act: -0.0000

Data Index: 281258 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9693. Min Act: -0.0000

Data Index: 809844 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9330. Min Act: -0.0000

Data Index: 604641 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9276. Min Act: -0.0000

Data Index: 222416 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9224. Min Act: -0.0000

Data Index: 92533 (C4 (Web Text))

Max Activating Token Index: 931