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

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

Neuron 1981 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2198. Min Act: -0.0001

Data Index: 766514 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2103. Min Act: -0.0001

Data Index: 654720 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1882. Min Act: -0.0001

Data Index: 198937 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1839. Min Act: -0.0001

Data Index: 494062 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1066125 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1900. Min Act: -0.0001

Data Index: 785698 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1796. Min Act: -0.0001

Data Index: 373531 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1767. Min Act: -0.0001

Data Index: 1293635 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1752. Min Act: -0.0001

Data Index: 102756 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1786. Min Act: -0.0001

Data Index: 578534 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1674. Min Act: -0.0001

Data Index: 769859 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1598. Min Act: -0.0001

Data Index: 480913 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1495. Min Act: -0.0001

Data Index: 932223 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1584. Min Act: -0.0001

Data Index: 269863 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1479. Min Act: -0.0001

Data Index: 205819 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1464. Min Act: -0.0001

Data Index: 409789 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1456. Min Act: -0.0001

Data Index: 94488 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1273140 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1301028 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1471. Min Act: -0.0001

Data Index: 806619 (C4 (Web Text))

Max Activating Token Index: 171