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

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

Neuron 1579 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.5505. Min Act: -0.0000

Data Index: 1343576 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1200811 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.1870. Min Act: -0.0000

Data Index: 113130 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.1643. Min Act: -0.0000

Data Index: 735297 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.1156. Min Act: -0.0000

Data Index: 639124 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.1084. Min Act: -0.0000

Data Index: 341308 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.1001. Min Act: -0.0000

Data Index: 529635 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.1074. Min Act: -0.0000

Data Index: 580774 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.0756. Min Act: -0.0000

Data Index: 530547 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.0773. Min Act: -0.0000

Data Index: 603458 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.0722. Min Act: -0.0000

Data Index: 238843 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 1.5505. Min Range: -1.5505

Max Act: 0.9946. Min Act: -0.0000

Data Index: 413348 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.0540. Min Act: -0.0000

Data Index: 284112 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1203633 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.0227. Min Act: -0.0000

Data Index: 323235 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 1.5505. Min Range: -1.5505

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1066022 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 1.5505. Min Range: -1.5505

Max Act: 0.9390. Min Act: -0.0000

Data Index: 787279 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.5505. Min Range: -1.5505

Max Act: 0.9892. Min Act: -0.0000

Data Index: 102405 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 1.5505. Min Range: -1.5505

Max Act: 0.9803. Min Act: -0.0000

Data Index: 369679 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 1.5505. Min Range: -1.5505

Max Act: 0.9015. Min Act: -0.0000

Data Index: 430972 (C4 (Web Text))

Max Activating Token Index: 187