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

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

Neuron 5808 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1645413 (Python Code)

Max Activating Token Index: 102

Text #1

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1480766 (Python Code)

Max Activating Token Index: 554

Text #2

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1630892 (Python Code)

Max Activating Token Index: 448

Text #3

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1421809 (Python Code)

Max Activating Token Index: 196

Text #4

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1623662 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1194973 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1551772 (Python Code)

Max Activating Token Index: 856

Text #7

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7550. Min Act: -0.0000

Data Index: 448930 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7362. Min Act: -0.0000

Data Index: 206394 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1505704 (Python Code)

Max Activating Token Index: 965

Text #10

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.6834. Min Act: -0.0000

Data Index: 920934 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1485635 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.5995. Min Act: -0.0000

Data Index: 608355 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1299042 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.5276. Min Act: -0.0000

Data Index: 3202 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1041518 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.5531. Min Act: -0.0000

Data Index: 380118 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.5678. Min Act: -0.0000

Data Index: 475018 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.5625. Min Act: 0.0000

Data Index: 26189 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1210859 (C4 (Web Text))

Max Activating Token Index: 249