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

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

Neuron 3503 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: 0.4701. Min Range: -0.4701

Max Act: 0.4701. Min Act: -0.0001

Data Index: 1048564 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3545. Min Act: -0.0001

Data Index: 912112 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3776. Min Act: -0.0000

Data Index: 602873 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4198. Min Act: -0.0000

Data Index: 80660 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3295. Min Act: -0.0001

Data Index: 524992 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3620. Min Act: -0.0000

Data Index: 856673 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4269. Min Act: -0.0000

Data Index: 152903 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1207666 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1301826 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3380. Min Act: -0.0001

Data Index: 381 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1313151 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3321. Min Act: -0.0000

Data Index: 625590 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3498. Min Act: -0.0000

Data Index: 20974 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3551. Min Act: -0.0000

Data Index: 319320 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3396. Min Act: -0.0000

Data Index: 777966 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2702. Min Act: -0.0001

Data Index: 345232 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2736. Min Act: -0.0000

Data Index: 53748 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2698. Min Act: -0.0001

Data Index: 616050 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2693. Min Act: -0.0000

Data Index: 679591 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3434. Min Act: -0.0000

Data Index: 807230 (C4 (Web Text))

Max Activating Token Index: 656