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

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

Neuron 2509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2510. Min Act: -0.0001

Data Index: 1359330 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.4039. Min Act: -0.0001

Data Index: 440895 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.2754. Min Act: -0.0001

Data Index: 924734 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.0409. Min Act: -0.0001

Data Index: 709930 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.4039. Min Range: -1.4039

Max Act: 1.0099. Min Act: -0.0001

Data Index: 605063 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.9063. Min Act: -0.0001

Data Index: 1475607 (Python Code)

Max Activating Token Index: 207

Text #6

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.8466. Min Act: -0.0001

Data Index: 1440849 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.8650. Min Act: -0.0001

Data Index: 1383264 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.7921. Min Act: -0.0001

Data Index: 756002 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.7970. Min Act: -0.0001

Data Index: 90954 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.8234. Min Act: -0.0001

Data Index: 391215 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.8208. Min Act: -0.0001

Data Index: 214301 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.8130. Min Act: -0.0001

Data Index: 182175 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.7629. Min Act: -0.0001

Data Index: 1050700 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.7604. Min Act: -0.0001

Data Index: 608819 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.7990. Min Act: -0.0001

Data Index: 1511713 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.6389. Min Act: -0.0001

Data Index: 517008 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.7896. Min Act: -0.0001

Data Index: 1528946 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.7525. Min Act: -0.0001

Data Index: 1540660 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 1.4039. Min Range: -1.4039

Max Act: 0.7300. Min Act: -0.0001

Data Index: 1381397 (Python Code)

Max Activating Token Index: 123