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

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

Neuron 454 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0067. Min Range: -6.0067

Max Act: 6.0067. Min Act: -0.0000

Data Index: 922468 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 6.0067. Min Range: -6.0067

Max Act: 5.7847. Min Act: -0.0000

Data Index: 552141 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 6.0067. Min Range: -6.0067

Max Act: 5.8286. Min Act: -0.0000

Data Index: 212255 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 6.0067. Min Range: -6.0067

Max Act: 4.6441. Min Act: -0.0000

Data Index: 874708 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 6.0067. Min Range: -6.0067

Max Act: 4.2858. Min Act: -0.0000

Data Index: 1321834 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 6.0067. Min Range: -6.0067

Max Act: 4.1719. Min Act: -0.0000

Data Index: 237459 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.9660. Min Act: -0.0000

Data Index: 1127160 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.9142. Min Act: -0.0000

Data Index: 1147674 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.8835. Min Act: -0.0000

Data Index: 1353703 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.9433. Min Act: -0.0000

Data Index: 1033249 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.8869. Min Act: -0.0000

Data Index: 26224 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.4652. Min Act: -0.0000

Data Index: 697783 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.5330. Min Act: -0.0000

Data Index: 1077869 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.4733. Min Act: -0.0000

Data Index: 936181 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.5692. Min Act: -0.0000

Data Index: 1080001 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.3553. Min Act: -0.0000

Data Index: 347938 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.3035. Min Act: -0.0000

Data Index: 1121319 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.3052. Min Act: -0.0000

Data Index: 1267320 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.2697. Min Act: -0.0000

Data Index: 803747 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 6.0067. Min Range: -6.0067

Max Act: 3.2220. Min Act: -0.0000

Data Index: 464342 (C4 (Web Text))

Max Activating Token Index: 937