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

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

Neuron 4056 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: 2.8862. Min Range: -2.8862

Max Act: 2.8253. Min Act: -0.0000

Data Index: 676773 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.8862. Min Act: -0.0000

Data Index: 917201 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.7160. Min Act: -0.0000

Data Index: 1086136 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.7665. Min Act: -0.0000

Data Index: 997150 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.5708. Min Act: -0.0000

Data Index: 1575845 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.4343. Min Act: -0.0000

Data Index: 1032403 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.4214. Min Act: -0.0000

Data Index: 271675 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.3813. Min Act: -0.0000

Data Index: 470197 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.4811. Min Act: -0.0000

Data Index: 439240 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.4720. Min Act: -0.0000

Data Index: 332344 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.2935. Min Act: -0.0000

Data Index: 1375194 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.4077. Min Act: -0.0000

Data Index: 314643 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.3995. Min Act: -0.0000

Data Index: 129546 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.5128. Min Act: -0.0000

Data Index: 1249673 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.5039. Min Act: -0.0000

Data Index: 1126368 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.3898. Min Act: -0.0000

Data Index: 1028644 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.2610. Min Act: -0.0000

Data Index: 1140458 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.2553. Min Act: -0.0000

Data Index: 280752 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.3641. Min Act: -0.0000

Data Index: 28194 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.4967. Min Act: -0.0000

Data Index: 762007 (C4 (Web Text))

Max Activating Token Index: 821