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

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

Neuron 5667 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: 0.7497. Min Range: -0.7497

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1097510 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.7497. Min Act: -0.0000

Data Index: 587537 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6412. Min Act: -0.0000

Data Index: 282303 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6971. Min Act: -0.0000

Data Index: 879059 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6312. Min Act: -0.0000

Data Index: 984743 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6075. Min Act: -0.0000

Data Index: 675747 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5947. Min Act: -0.0000

Data Index: 599659 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6123. Min Act: -0.0000

Data Index: 385956 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1123068 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1213498 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1485340 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6051. Min Act: -0.0000

Data Index: 625151 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1020101 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5818. Min Act: -0.0000

Data Index: 473551 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5609. Min Act: -0.0000

Data Index: 14534 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5621. Min Act: -0.0000

Data Index: 792997 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5929. Min Act: -0.0000

Data Index: 131165 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1045516 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5090. Min Act: -0.0000

Data Index: 696594 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5087. Min Act: -0.0000

Data Index: 683972 (C4 (Web Text))

Max Activating Token Index: 97