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

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

Neuron 689 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.8290. Min Act: -0.0001

Data Index: 991230 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.3728. Min Act: -0.0000

Data Index: 913439 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.5961. Min Act: -0.0000

Data Index: 954105 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.5514. Min Act: -0.0000

Data Index: 152507 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.3386. Min Act: -0.0000

Data Index: 138574 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.2886. Min Act: -0.0000

Data Index: 546390 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.4033. Min Act: -0.0000

Data Index: 1095366 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.0865. Min Act: -0.0000

Data Index: 155659 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.3298. Min Act: -0.0000

Data Index: 778631 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.3387. Min Act: -0.0000

Data Index: 1340050 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.2002. Min Act: -0.0000

Data Index: 1215624 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.1538. Min Act: -0.0000

Data Index: 661214 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.1493. Min Act: -0.0000

Data Index: 1311113 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.1296. Min Act: -0.0000

Data Index: 375965 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.0097. Min Act: -0.0000

Data Index: 66304 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.2354. Min Act: -0.0000

Data Index: 691798 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.1173. Min Act: -0.0000

Data Index: 409476 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.0863. Min Act: -0.0001

Data Index: 616509 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.1686. Min Act: -0.0000

Data Index: 1007762 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.0442. Min Act: -0.0000

Data Index: 1050955 (C4 (Web Text))

Max Activating Token Index: 58