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

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

Neuron 3259 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.7836. Min Act: -0.0000

Data Index: 968816 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.5914. Min Act: -0.0000

Data Index: 451749 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.5759. Min Act: -0.0000

Data Index: 499398 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.6999. Min Act: -0.0000

Data Index: 745001 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.2510. Min Act: -0.0000

Data Index: 1167782 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.5817. Min Act: -0.0000

Data Index: 1340599 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.4364. Min Act: -0.0000

Data Index: 987736 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.5342. Min Act: -0.0000

Data Index: 409572 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.2240. Min Act: -0.0000

Data Index: 1281769 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.4771. Min Act: -0.0000

Data Index: 668363 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.3461. Min Act: -0.0000

Data Index: 1245632 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.3156. Min Act: -0.0000

Data Index: 684848 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.4343. Min Act: -0.0000

Data Index: 572456 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.2575. Min Act: -0.0000

Data Index: 647825 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.2187. Min Act: -0.0000

Data Index: 36369 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.0442. Min Act: -0.0000

Data Index: 665626 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 2.7836. Min Range: -2.7836

Max Act: 1.9448. Min Act: -0.0000

Data Index: 599668 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.0216. Min Act: -0.0000

Data Index: 818592 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.1174. Min Act: -0.0000

Data Index: 715695 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 2.7836. Min Range: -2.7836

Max Act: 2.1355. Min Act: -0.0000

Data Index: 1087602 (C4 (Web Text))

Max Activating Token Index: 49