Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 107 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0895. Min Act: -0.0000

Data Index: 215290 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0859. Min Act: -0.0000

Data Index: 483600 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0912. Min Act: -0.0001

Data Index: 745289 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0891. Min Act: -0.0000

Data Index: 194721 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0892. Min Act: -0.0001

Data Index: 819840 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1123682 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0930. Min Act: -0.0001

Data Index: 679576 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0825. Min Act: -0.0001

Data Index: 456793 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0864. Min Act: -0.0001

Data Index: 387567 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0820. Min Act: -0.0001

Data Index: 201124 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1238207 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0845. Min Act: -0.0001

Data Index: 391291 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1420422 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0871. Min Act: -0.0001

Data Index: 214218 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0788. Min Act: -0.0000

Data Index: 852654 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0820. Min Act: -0.0000

Data Index: 465627 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0783. Min Act: -0.0000

Data Index: 357066 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1650341 (Python Code)

Max Activating Token Index: 495

Text #18

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1349175 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0740. Min Act: -0.0000

Data Index: 223677 (C4 (Web Text))

Max Activating Token Index: 942