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

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

Neuron 4563 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: 1.2211. Min Range: -1.2211

Max Act: 1.2211. Min Act: -0.0000

Data Index: 342188 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.2026. Min Act: -0.0000

Data Index: 305184 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1269504 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0830. Min Act: -0.0000

Data Index: 473990 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1198. Min Act: -0.0000

Data Index: 452474 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9645. Min Act: -0.0000

Data Index: 136915 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9509. Min Act: -0.0000

Data Index: 484403 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1278396 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1345644 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9352. Min Act: -0.0000

Data Index: 901090 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9207. Min Act: -0.0000

Data Index: 197754 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8972. Min Act: -0.0000

Data Index: 364813 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1635885 (Python Code)

Max Activating Token Index: 855

Text #13

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1570730 (Python Code)

Max Activating Token Index: 850

Text #14

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1152935 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8724. Min Act: -0.0000

Data Index: 803630 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8973. Min Act: -0.0000

Data Index: 431535 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8719. Min Act: -0.0000

Data Index: 262497 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1550589 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8396. Min Act: -0.0000

Data Index: 560157 (C4 (Web Text))

Max Activating Token Index: 587