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

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

Neuron 1020 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.4668. Min Act: -0.0001

Data Index: 291348 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.4302. Min Act: -0.0001

Data Index: 1215467 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1321361 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.3348. Min Act: -0.0000

Data Index: 1292144 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2529. Min Act: -0.0000

Data Index: 1312786 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2666. Min Act: -0.0000

Data Index: 249597 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1921. Min Act: -0.0001

Data Index: 244639 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1796. Min Act: -0.0001

Data Index: 229989 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1058392 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1189. Min Act: -0.0001

Data Index: 163784 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1021. Min Act: -0.0000

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.0108. Min Act: -0.0000

Data Index: 533744 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.0736. Min Act: -0.0001

Data Index: 1024588 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.0561. Min Act: -0.0000

Data Index: 376871 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 1.4668. Min Range: -1.4668

Max Act: 0.9800. Min Act: -0.0001

Data Index: 1096495 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.0143. Min Act: -0.0000

Data Index: 1114536 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.4668. Min Range: -1.4668

Max Act: 0.9518. Min Act: -0.0000

Data Index: 186256 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.0119. Min Act: -0.0000

Data Index: 610993 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.4668. Min Range: -1.4668

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1060937 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.4668. Min Range: -1.4668

Max Act: 0.9065. Min Act: -0.0001

Data Index: 338410 (C4 (Web Text))

Max Activating Token Index: 240