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

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

Neuron 1927 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: 0.3848. Min Range: -0.3848

Max Act: 0.3848. Min Act: -0.0000

Data Index: 793502 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3729. Min Act: -0.0000

Data Index: 202776 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3623. Min Act: -0.0001

Data Index: 969693 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3550. Min Act: -0.0001

Data Index: 1239107 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1208617 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1075178 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3375. Min Act: -0.0001

Data Index: 1202946 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3306. Min Act: -0.0001

Data Index: 1252512 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3170. Min Act: -0.0000

Data Index: 35516 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3367. Min Act: -0.0001

Data Index: 1040842 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3265. Min Act: -0.0000

Data Index: 117644 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3147. Min Act: -0.0001

Data Index: 1204485 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3033. Min Act: -0.0000

Data Index: 609708 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3031. Min Act: -0.0000

Data Index: 283351 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1231121 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2879. Min Act: -0.0001

Data Index: 1218620 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1180099 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2736. Min Act: -0.0001

Data Index: 469188 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1216338 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2800. Min Act: -0.0000

Data Index: 395464 (C4 (Web Text))

Max Activating Token Index: 844