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

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

Neuron 1453 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5988. Min Act: -0.0000

Data Index: 665699 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5843. Min Act: -0.0000

Data Index: 697090 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5684. Min Act: -0.0000

Data Index: 167962 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5685. Min Act: -0.0000

Data Index: 93043 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4963. Min Act: -0.0000

Data Index: 999605 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4805. Min Act: -0.0000

Data Index: 781688 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4880. Min Act: -0.0000

Data Index: 579163 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1191512 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4403. Min Act: -0.0000

Data Index: 65083 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3762. Min Act: -0.0000

Data Index: 127282 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3966. Min Act: -0.0000

Data Index: 757376 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3618. Min Act: -0.0000

Data Index: 862311 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3477. Min Act: -0.0000

Data Index: 391777 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3718. Min Act: -0.0000

Data Index: 427644 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3928. Min Act: -0.0000

Data Index: 703914 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3650. Min Act: -0.0000

Data Index: 326395 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3606. Min Act: -0.0000

Data Index: 531088 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3528. Min Act: -0.0000

Data Index: 152395 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1012923 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3499. Min Act: -0.0000

Data Index: 889743 (C4 (Web Text))

Max Activating Token Index: 514