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

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

Neuron 3509 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: 0.6200. Min Range: -0.6200

Max Act: 0.6200. Min Act: -0.0000

Data Index: 503852 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1465578 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.5002. Min Act: -0.0000

Data Index: 258089 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1587924 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.5314. Min Act: -0.0000

Data Index: 772461 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1524586 (Python Code)

Max Activating Token Index: 269

Text #6

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4636. Min Act: -0.0000

Data Index: 33841 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4311. Min Act: -0.0000

Data Index: 504932 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4602. Min Act: -0.0000

Data Index: 530502 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4453. Min Act: -0.0000

Data Index: 742329 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4572. Min Act: -0.0000

Data Index: 234124 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1001449 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1646115 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1480394 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1599753 (Python Code)

Max Activating Token Index: 910

Text #15

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1380361 (Python Code)

Max Activating Token Index: 809

Text #16

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4190. Min Act: -0.0000

Data Index: 725959 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4126. Min Act: -0.0000

Data Index: 217908 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.4218. Min Act: -0.0000

Data Index: 929242 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.6200. Min Range: -0.6200

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1517098 (Python Code)

Max Activating Token Index: 913