Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 453 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.3485. Min Act: -0.0001

Data Index: 67829 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1941. Min Act: -0.0001

Data Index: 1128585 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.4407. Min Act: -0.0001

Data Index: 527096 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1906. Min Act: -0.0001

Data Index: 695264 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1893. Min Act: -0.0001

Data Index: 611206 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.2935. Min Act: -0.0001

Data Index: 419835 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.0037. Min Act: -0.0001

Data Index: 587269 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1443. Min Act: -0.0001

Data Index: 935436 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1356. Min Act: -0.0001

Data Index: 485308 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1643. Min Act: -0.0001

Data Index: 108807 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1934. Min Act: -0.0001

Data Index: 788624 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.2179. Min Act: -0.0001

Data Index: 322295 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.2008. Min Act: -0.0001

Data Index: 1037654 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.0719. Min Act: -0.0001

Data Index: 108085 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.0244. Min Act: -0.0001

Data Index: 1249329 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1000. Min Act: -0.0001

Data Index: 1106549 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1702. Min Act: -0.0001

Data Index: 282699 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.1068. Min Act: -0.0001

Data Index: 1026017 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.4407. Min Range: -1.4407

Max Act: 0.9490. Min Act: -0.0001

Data Index: 557898 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 1.4407. Min Range: -1.4407

Max Act: 1.0984. Min Act: -0.0001

Data Index: 600089 (C4 (Web Text))

Max Activating Token Index: 461