Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2980 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.5356. Min Act: -0.0000

Data Index: 62593 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.5814. Min Act: -0.0000

Data Index: 3623 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1237713 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4269. Min Act: -0.0000

Data Index: 585362 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4687. Min Act: -0.0000

Data Index: 834209 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4491. Min Act: -0.0000

Data Index: 874199 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.5297. Min Act: -0.0000

Data Index: 96781 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4628. Min Act: -0.0000

Data Index: 20769 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1118759 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1093214 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4323. Min Act: -0.0000

Data Index: 876361 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4866. Min Act: -0.0000

Data Index: 706221 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4534. Min Act: -0.0000

Data Index: 462052 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1096381 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4269. Min Act: -0.0000

Data Index: 875743 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4546. Min Act: -0.0000

Data Index: 912273 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4416. Min Act: -0.0000

Data Index: 591966 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.3930. Min Act: -0.0000

Data Index: 932087 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.3748. Min Act: -0.0000

Data Index: 838483 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.4827. Min Act: -0.0000

Data Index: 949847 (C4 (Web Text))

Max Activating Token Index: 77