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

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

Neuron 1779 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0000

Data Index: 160922 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0648. Min Act: -0.0000

Data Index: 244807 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0588. Min Act: -0.0000

Data Index: 298084 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0560. Min Act: -0.0000

Data Index: 95016 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0561. Min Act: -0.0000

Data Index: 1118699 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0532. Min Act: -0.0000

Data Index: 700919 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0539. Min Act: -0.0000

Data Index: 125070 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0523. Min Act: -0.0000

Data Index: 938071 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0484. Min Act: -0.0000

Data Index: 744561 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1300762 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0506. Min Act: -0.0000

Data Index: 163890 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0482. Min Act: -0.0000

Data Index: 928748 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0480. Min Act: -0.0000

Data Index: 904 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0491. Min Act: -0.0000

Data Index: 65753 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0428. Min Act: -0.0000

Data Index: 174669 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0464. Min Act: -0.0000

Data Index: 214867 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0433. Min Act: -0.0000

Data Index: 1550239 (Python Code)

Max Activating Token Index: 408

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0444. Min Act: -0.0000

Data Index: 994629 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0462. Min Act: -0.0000

Data Index: 963433 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0441. Min Act: -0.0000

Data Index: 807763 (C4 (Web Text))

Max Activating Token Index: 107