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

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

Neuron 1692 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1021. Min Range: -2.1021

Max Act: 2.1021. Min Act: -0.0000

Data Index: 575572 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.8732. Min Act: -0.0000

Data Index: 176863 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.8851. Min Act: -0.0000

Data Index: 633431 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.7788. Min Act: -0.0000

Data Index: 730754 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.8270. Min Act: -0.0000

Data Index: 461775 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.7250. Min Act: -0.0000

Data Index: 210206 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.6056. Min Act: -0.0000

Data Index: 613570 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.6799. Min Act: -0.0000

Data Index: 227664 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1042027 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.6590. Min Act: -0.0000

Data Index: 822414 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5630. Min Act: -0.0000

Data Index: 792001 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1366046 (Python Code)

Max Activating Token Index: 547

Text #12

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5244. Min Act: -0.0000

Data Index: 860751 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5109. Min Act: -0.0000

Data Index: 201786 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.4427. Min Act: -0.0000

Data Index: 34667 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.3220. Min Act: -0.0000

Data Index: 777951 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.3854. Min Act: -0.0000

Data Index: 1349090 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.3738. Min Act: -0.0000

Data Index: 613602 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1176573 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.4496. Min Act: -0.0000

Data Index: 1060098 (C4 (Web Text))

Max Activating Token Index: 528