Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 832 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1498918 (Python Code)

Max Activating Token Index: 683

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0578. Min Act: -0.0001

Data Index: 192237 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1409245 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1517398 (Python Code)

Max Activating Token Index: 507

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1436377 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0552. Min Act: -0.0002

Data Index: 829472 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1551355 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1399202 (Python Code)

Max Activating Token Index: 550

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0520. Min Act: -0.0002

Data Index: 181280 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1444308 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1564465 (Python Code)

Max Activating Token Index: 572

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0521. Min Act: -0.0002

Data Index: 912964 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1624689 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1616207 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0463. Min Act: -0.0002

Data Index: 187008 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1512789 (Python Code)

Max Activating Token Index: 600

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1431372 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1029682 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1215051 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1349532 (C4 (Web Text))

Max Activating Token Index: 821