Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 946 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6645. Min Act: -0.0001

Data Index: 1644108 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5820. Min Act: -0.0001

Data Index: 1550830 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5242. Min Act: -0.0001

Data Index: 1632917 (Python Code)

Max Activating Token Index: 662

Text #3

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5055. Min Act: -0.0001

Data Index: 1563048 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5105. Min Act: -0.0001

Data Index: 1537683 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4304. Min Act: -0.0001

Data Index: 1460243 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4646. Min Act: -0.0001

Data Index: 1435428 (Python Code)

Max Activating Token Index: 815

Text #7

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4554. Min Act: -0.0001

Data Index: 1139623 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4767. Min Act: -0.0001

Data Index: 1567098 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4742. Min Act: -0.0001

Data Index: 121663 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5105. Min Act: -0.0001

Data Index: 1050741 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4730. Min Act: -0.0001

Data Index: 1469139 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4729. Min Act: -0.0001

Data Index: 1604579 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4578. Min Act: -0.0001

Data Index: 1533106 (Python Code)

Max Activating Token Index: 876

Text #14

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4703. Min Act: -0.0001

Data Index: 1530685 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1429285 (Python Code)

Max Activating Token Index: 338

Text #16

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4740. Min Act: -0.0001

Data Index: 1646782 (Python Code)

Max Activating Token Index: 1020

Text #17

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4385. Min Act: -0.0001

Data Index: 1547324 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1438527 (Python Code)

Max Activating Token Index: 314

Text #19

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4319. Min Act: -0.0001

Data Index: 1248462 (C4 (Web Text))

Max Activating Token Index: 988