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

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

Neuron 4420 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1382208 (Python Code)

Max Activating Token Index: 369

Text #1

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0491. Min Act: -0.0003

Data Index: 913170 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1175618 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0498. Min Act: -0.0002

Data Index: 525496 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0476. Min Act: -0.0002

Data Index: 938809 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1272852 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0460. Min Act: -0.0002

Data Index: 949833 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1153962 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0451. Min Act: -0.0002

Data Index: 323542 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1109781 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0447. Min Act: -0.0002

Data Index: 499637 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0452. Min Act: -0.0002

Data Index: 885413 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0449. Min Act: -0.0003

Data Index: 491033 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0449. Min Act: -0.0002

Data Index: 825945 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1399340 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0438. Min Act: -0.0002

Data Index: 588134 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0417. Min Act: -0.0002

Data Index: 356422 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1149638 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1401328 (Python Code)

Max Activating Token Index: 517

Text #19

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0427. Min Act: -0.0002

Data Index: 314348 (C4 (Web Text))

Max Activating Token Index: 396