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

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

Neuron 2585 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7115. Min Range: -2.7115

Max Act: 2.7115. Min Act: -0.0000

Data Index: 66745 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 2.7115. Min Range: -2.7115

Max Act: 2.1635. Min Act: -0.0000

Data Index: 916233 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 2.7115. Min Range: -2.7115

Max Act: 2.1053. Min Act: -0.0000

Data Index: 376810 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.9638. Min Act: -0.0000

Data Index: 1113664 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 2.7115. Min Range: -2.7115

Max Act: 2.1503. Min Act: -0.0000

Data Index: 1099133 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 2.7115. Min Range: -2.7115

Max Act: 2.2266. Min Act: -0.0000

Data Index: 1182932 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.9979. Min Act: -0.0000

Data Index: 221766 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.8350. Min Act: -0.0000

Data Index: 1131666 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.9553. Min Act: -0.0000

Data Index: 1344048 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.8548. Min Act: -0.0000

Data Index: 419698 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.9474. Min Act: -0.0000

Data Index: 1005046 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.8255. Min Act: -0.0000

Data Index: 81276 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1126995 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.8441. Min Act: -0.0000

Data Index: 737167 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.5971. Min Act: -0.0000

Data Index: 663996 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.7251. Min Act: -0.0000

Data Index: 1183805 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.8877. Min Act: -0.0000

Data Index: 604713 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.7470. Min Act: -0.0000

Data Index: 637112 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 2.7115. Min Range: -2.7115

Max Act: 2.0688. Min Act: -0.0000

Data Index: 227744 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 2.7115. Min Range: -2.7115

Max Act: 1.7558. Min Act: -0.0000

Data Index: 657672 (C4 (Web Text))

Max Activating Token Index: 213