Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1389 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0663. Min Range: -2.0663

Max Act: 2.0486. Min Act: -0.0000

Data Index: 80701 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.9374. Min Act: -0.0001

Data Index: 1200711 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.9119. Min Act: -0.0000

Data Index: 119926 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.8691. Min Act: -0.0000

Data Index: 617312 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 2.0663. Min Range: -2.0663

Max Act: 2.0663. Min Act: -0.0000

Data Index: 136573 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.7308. Min Act: -0.0000

Data Index: 457330 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.6737. Min Act: -0.0000

Data Index: 630971 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.8283. Min Act: -0.0001

Data Index: 37230 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.8165. Min Act: -0.0000

Data Index: 572366 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.7917. Min Act: -0.0000

Data Index: 546650 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.6547. Min Act: -0.0000

Data Index: 362155 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.7242. Min Act: -0.0000

Data Index: 138560 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.6336. Min Act: -0.0000

Data Index: 324837 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.5297. Min Act: -0.0000

Data Index: 937790 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.6764. Min Act: -0.0000

Data Index: 946813 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.6567. Min Act: -0.0000

Data Index: 755910 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.5747. Min Act: -0.0001

Data Index: 162087 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.4944. Min Act: -0.0000

Data Index: 129766 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.6644. Min Act: -0.0001

Data Index: 32865 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 2.0663. Min Range: -2.0663

Max Act: 1.5543. Min Act: -0.0000

Data Index: 156647 (C4 (Web Text))

Max Activating Token Index: 325