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

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

Neuron 4460 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1017796 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1279508 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1182371 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4594. Min Act: -0.0000

Data Index: 513993 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4338. Min Act: -0.0000

Data Index: 572308 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1159526 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4118. Min Act: -0.0000

Data Index: 624467 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4391. Min Act: -0.0000

Data Index: 984995 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1170538 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1176236 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1060173 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1276953 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3923. Min Act: -0.0000

Data Index: 926502 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4011. Min Act: -0.0000

Data Index: 69114 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3978. Min Act: -0.0000

Data Index: 956807 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1328843 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1001304 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3561. Min Act: -0.0000

Data Index: 341714 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1300868 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.3281. Min Act: -0.0000

Data Index: 458220 (C4 (Web Text))

Max Activating Token Index: 277