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

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

Neuron 6024 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1312897 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1134591 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1216351 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0545. Min Act: -0.0000

Data Index: 290925 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0634. Min Act: -0.0000

Data Index: 755644 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0537. Min Act: -0.0000

Data Index: 998659 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0575. Min Act: -0.0000

Data Index: 234058 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0552. Min Act: -0.0000

Data Index: 466798 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1218048 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0546. Min Act: -0.0000

Data Index: 359571 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0510. Min Act: -0.0000

Data Index: 968313 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1223228 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0551. Min Act: -0.0000

Data Index: 267005 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0491. Min Act: -0.0000

Data Index: 913640 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0489. Min Act: -0.0000

Data Index: 110261 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0495. Min Act: -0.0000

Data Index: 21761 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0485. Min Act: -0.0000

Data Index: 632774 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0461. Min Act: -0.0000

Data Index: 223980 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0460. Min Act: -0.0000

Data Index: 734779 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0467. Min Act: -0.0000

Data Index: 361186 (C4 (Web Text))

Max Activating Token Index: 284