Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 591 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1912. Min Act: -0.0001

Data Index: 693691 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1767. Min Act: -0.0001

Data Index: 143269 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1768. Min Act: -0.0001

Data Index: 5057 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1745. Min Act: -0.0001

Data Index: 113323 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1746. Min Act: -0.0001

Data Index: 917645 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1787. Min Act: -0.0001

Data Index: 292912 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1655. Min Act: -0.0001

Data Index: 1060416 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1615. Min Act: -0.0001

Data Index: 193969 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1550. Min Act: -0.0001

Data Index: 16321 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1027165 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1602. Min Act: -0.0001

Data Index: 786902 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1602. Min Act: -0.0001

Data Index: 533009 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1595. Min Act: -0.0001

Data Index: 447879 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1532. Min Act: -0.0001

Data Index: 485100 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1586. Min Act: -0.0001

Data Index: 66421 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1007643 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1300397 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1559. Min Act: -0.0000

Data Index: 492411 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1548. Min Act: -0.0001

Data Index: 191228 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1356507 (C4 (Web Text))

Max Activating Token Index: 549