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

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

Neuron 5015 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: 1.9566. Min Range: -1.9566

Max Act: 1.9566. Min Act: -0.0001

Data Index: 1522239 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.8040. Min Act: -0.0001

Data Index: 1405463 (Python Code)

Max Activating Token Index: 259

Text #2

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.7524. Min Act: -0.0001

Data Index: 1654485 (Python Code)

Max Activating Token Index: 328

Text #3

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.9016. Min Act: -0.0001

Data Index: 1614684 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.8925. Min Act: -0.0001

Data Index: 1578753 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.8522. Min Act: -0.0001

Data Index: 1458988 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.7117. Min Act: -0.0001

Data Index: 1453326 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.8931. Min Act: -0.0001

Data Index: 1360462 (Python Code)

Max Activating Token Index: 760

Text #8

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.7903. Min Act: -0.0001

Data Index: 1603817 (Python Code)

Max Activating Token Index: 589

Text #9

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.8101. Min Act: -0.0001

Data Index: 1491671 (Python Code)

Max Activating Token Index: 198

Text #10

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.6846. Min Act: -0.0001

Data Index: 1500410 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.7780. Min Act: -0.0001

Data Index: 1395934 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.7764. Min Act: -0.0001

Data Index: 1526899 (Python Code)

Max Activating Token Index: 232

Text #13

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.7746. Min Act: -0.0001

Data Index: 933025 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.8537. Min Act: -0.0000

Data Index: 1089374 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.8459. Min Act: -0.0000

Data Index: 235582 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.7593. Min Act: -0.0001

Data Index: 1443328 (Python Code)

Max Activating Token Index: 543

Text #17

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.7464. Min Act: -0.0001

Data Index: 1616527 (Python Code)

Max Activating Token Index: 816

Text #18

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.7363. Min Act: -0.0001

Data Index: 1381466 (Python Code)

Max Activating Token Index: 315

Text #19

Max Range: 1.9566. Min Range: -1.9566

Max Act: 1.6477. Min Act: -0.0001

Data Index: 1655190 (Python Code)

Max Activating Token Index: 768