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

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

Neuron 4351 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: 0.0702. Min Range: -0.0702

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1196226 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0664. Min Act: -0.0000

Data Index: 27392 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0569. Min Act: -0.0000

Data Index: 172619 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0537. Min Act: -0.0000

Data Index: 956810 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0637. Min Act: -0.0000

Data Index: 495519 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0546. Min Act: -0.0000

Data Index: 790124 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1241904 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0549. Min Act: -0.0000

Data Index: 694890 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0533. Min Act: -0.0000

Data Index: 115069 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0524. Min Act: -0.0000

Data Index: 873808 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0518. Min Act: -0.0000

Data Index: 858336 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0516. Min Act: 0.0000

Data Index: 515761 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0532. Min Act: -0.0000

Data Index: 290378 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0514. Min Act: -0.0000

Data Index: 343844 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0523. Min Act: -0.0000

Data Index: 96849 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1007083 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0462. Min Act: -0.0000

Data Index: 371543 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0525. Min Act: -0.0000

Data Index: 281622 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0507. Min Act: -0.0000

Data Index: 569642 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0515. Min Act: -0.0000

Data Index: 63771 (C4 (Web Text))

Max Activating Token Index: 5