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

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

Neuron 892 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0004

Data Index: 46593 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0619. Min Act: -0.0004

Data Index: 306769 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0653. Min Act: -0.0004

Data Index: 841435 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0596. Min Act: -0.0004

Data Index: 1226933 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0568. Min Act: -0.0004

Data Index: 147757 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0523. Min Act: -0.0004

Data Index: 179899 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0573. Min Act: -0.0004

Data Index: 1168780 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0555. Min Act: -0.0004

Data Index: 897191 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0540. Min Act: -0.0004

Data Index: 927997 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0546. Min Act: -0.0004

Data Index: 464996 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0554. Min Act: -0.0004

Data Index: 119975 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0540. Min Act: -0.0004

Data Index: 1221953 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0513. Min Act: -0.0004

Data Index: 847735 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0543. Min Act: -0.0004

Data Index: 512893 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0553. Min Act: -0.0004

Data Index: 325851 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0519. Min Act: -0.0004

Data Index: 1342659 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0538. Min Act: -0.0004

Data Index: 614504 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0529. Min Act: -0.0004

Data Index: 377217 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0526. Min Act: -0.0004

Data Index: 1202290 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0515. Min Act: -0.0004

Data Index: 710428 (C4 (Web Text))

Max Activating Token Index: 150