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

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

Neuron 966 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: 1.1437. Min Range: -1.1437

Max Act: 1.1437. Min Act: -0.0000

Data Index: 647961 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 1.1437. Min Range: -1.1437

Max Act: 1.1160. Min Act: -0.0000

Data Index: 159597 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.9974. Min Act: -0.0000

Data Index: 9488 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1012607 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.9071. Min Act: -0.0001

Data Index: 267645 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.9181. Min Act: -0.0000

Data Index: 387456 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.9826. Min Act: -0.0000

Data Index: 82565 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8959. Min Act: -0.0001

Data Index: 602586 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8027. Min Act: -0.0000

Data Index: 683795 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.9385. Min Act: -0.0000

Data Index: 346261 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.7736. Min Act: -0.0000

Data Index: 44183 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8422. Min Act: -0.0000

Data Index: 804820 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1181245 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1324307 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1128045 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8743. Min Act: -0.0001

Data Index: 771952 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1170300 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8170. Min Act: -0.0001

Data Index: 360085 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.8435. Min Act: -0.0000

Data Index: 713457 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.1437. Min Range: -1.1437

Max Act: 0.7465. Min Act: -0.0000

Data Index: 662836 (C4 (Web Text))

Max Activating Token Index: 916