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

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

Neuron 1766 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1147. Min Range: -2.1147

Max Act: 2.1147. Min Act: -0.0000

Data Index: 17571 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.5260. Min Act: -0.0000

Data Index: 59534 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.5166. Min Act: -0.0000

Data Index: 1203371 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.5474. Min Act: -0.0000

Data Index: 445491 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.5051. Min Act: -0.0000

Data Index: 305371 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.5193. Min Act: -0.0000

Data Index: 1327514 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.5526. Min Act: -0.0000

Data Index: 602768 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.4141. Min Act: -0.0000

Data Index: 968968 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.3640. Min Act: -0.0000

Data Index: 916741 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.4742. Min Act: -0.0000

Data Index: 628317 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.4052. Min Act: -0.0000

Data Index: 289671 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1125370 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.3283. Min Act: -0.0000

Data Index: 211166 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.2490. Min Act: -0.0000

Data Index: 384231 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.3307. Min Act: -0.0000

Data Index: 935104 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1346547 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.2759. Min Act: -0.0000

Data Index: 486794 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.3435. Min Act: -0.0000

Data Index: 950895 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1289574 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 2.1147. Min Range: -2.1147

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1513777 (Python Code)

Max Activating Token Index: 817