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

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

Neuron 415 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: 0.6809. Min Range: -0.6809

Max Act: 0.6634. Min Act: -0.0000

Data Index: 700709 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1099828 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6198. Min Act: -0.0000

Data Index: 375955 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6809. Min Act: -0.0000

Data Index: 374326 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5504. Min Act: -0.0000

Data Index: 58559 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1149687 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1006446 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6577. Min Act: -0.0000

Data Index: 701739 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5822. Min Act: -0.0000

Data Index: 389618 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5824. Min Act: -0.0000

Data Index: 278811 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5837. Min Act: -0.0000

Data Index: 536659 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5534. Min Act: -0.0000

Data Index: 437651 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6254. Min Act: -0.0000

Data Index: 444095 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6000. Min Act: -0.0000

Data Index: 871562 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1056592 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5694. Min Act: -0.0000

Data Index: 982577 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5674. Min Act: -0.0000

Data Index: 895293 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5265. Min Act: -0.0000

Data Index: 384947 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5556. Min Act: -0.0000

Data Index: 142470 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1300762 (C4 (Web Text))

Max Activating Token Index: 252