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

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

Neuron 4267 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1042066 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.5709. Min Act: -0.0000

Data Index: 782578 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1141059 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4626. Min Act: -0.0000

Data Index: 753045 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1243919 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4442. Min Act: -0.0000

Data Index: 152892 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4268. Min Act: -0.0000

Data Index: 368957 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4539. Min Act: -0.0000

Data Index: 501685 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4352. Min Act: -0.0000

Data Index: 703275 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4338. Min Act: -0.0000

Data Index: 610593 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1236723 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4327. Min Act: -0.0000

Data Index: 194173 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4506. Min Act: -0.0000

Data Index: 695244 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4212. Min Act: -0.0000

Data Index: 933542 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4141. Min Act: -0.0000

Data Index: 4617 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1087692 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.3917. Min Act: -0.0000

Data Index: 325896 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.3782. Min Act: -0.0000

Data Index: 211363 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.3890. Min Act: -0.0000

Data Index: 805790 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1146209 (C4 (Web Text))

Max Activating Token Index: 1014