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

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

Neuron 1681 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.3444. Min Act: -0.0000

Data Index: 336142 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.2076. Min Act: -0.0000

Data Index: 1588348 (Python Code)

Max Activating Token Index: 954

Text #2

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.1896. Min Act: -0.0000

Data Index: 251695 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.0958. Min Act: -0.0000

Data Index: 885517 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1377142 (Python Code)

Max Activating Token Index: 727

Text #5

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1306869 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.0568. Min Act: -0.0000

Data Index: 415248 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.0891. Min Act: -0.0000

Data Index: 917583 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1404343 (Python Code)

Max Activating Token Index: 243

Text #9

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1146232 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1559642 (Python Code)

Max Activating Token Index: 557

Text #11

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.0704. Min Act: -0.0000

Data Index: 28290 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1316722 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.8982. Min Act: -0.0000

Data Index: 240611 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.9722. Min Act: -0.0000

Data Index: 428191 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1639754 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.9441. Min Act: -0.0000

Data Index: 9599 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 1.3444. Min Range: -1.3444

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1410061 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1652553 (Python Code)

Max Activating Token Index: 521

Text #19

Max Range: 1.3444. Min Range: -1.3444

Max Act: 0.9424. Min Act: -0.0000

Data Index: 29779 (C4 (Web Text))

Max Activating Token Index: 692