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

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

Neuron 3736 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.2724. Min Act: -0.0001

Data Index: 489170 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.2373. Min Act: -0.0001

Data Index: 142712 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1790. Min Act: -0.0001

Data Index: 891327 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1848. Min Act: -0.0001

Data Index: 343471 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1643. Min Act: -0.0000

Data Index: 292549 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1692. Min Act: -0.0001

Data Index: 555649 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1263306 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1610. Min Act: -0.0001

Data Index: 896786 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1584. Min Act: -0.0001

Data Index: 535931 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1655. Min Act: -0.0001

Data Index: 332098 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1454. Min Act: -0.0001

Data Index: 153284 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1458. Min Act: -0.0001

Data Index: 842037 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1383. Min Act: -0.0001

Data Index: 648660 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1458. Min Act: -0.0001

Data Index: 807722 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1407. Min Act: -0.0001

Data Index: 17904 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1037208 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1284. Min Act: -0.0000

Data Index: 665892 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1288. Min Act: -0.0000

Data Index: 219313 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1269. Min Act: -0.0001

Data Index: 393358 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.2724. Min Range: -0.2724

Max Act: 0.1106. Min Act: -0.0001

Data Index: 786387 (C4 (Web Text))

Max Activating Token Index: 236