Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4012 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1021. Min Range: -2.1021

Max Act: 2.1021. Min Act: -0.0001

Data Index: 1531952 (Python Code)

Max Activating Token Index: 947

Text #1

Max Range: 2.1021. Min Range: -2.1021

Max Act: 2.0278. Min Act: -0.0001

Data Index: 1402181 (Python Code)

Max Activating Token Index: 618

Text #2

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.8220. Min Act: -0.0001

Data Index: 1524085 (Python Code)

Max Activating Token Index: 603

Text #3

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.7475. Min Act: -0.0001

Data Index: 1595519 (Python Code)

Max Activating Token Index: 817

Text #4

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.6732. Min Act: -0.0001

Data Index: 1597728 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.7200. Min Act: -0.0001

Data Index: 1600636 (Python Code)

Max Activating Token Index: 139

Text #6

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.6254. Min Act: -0.0001

Data Index: 1385620 (Python Code)

Max Activating Token Index: 669

Text #7

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.6488. Min Act: -0.0001

Data Index: 1417178 (Python Code)

Max Activating Token Index: 777

Text #8

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.4501. Min Act: -0.0001

Data Index: 1361364 (Python Code)

Max Activating Token Index: 964

Text #9

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5665. Min Act: -0.0001

Data Index: 1409102 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.6773. Min Act: -0.0001

Data Index: 1420494 (Python Code)

Max Activating Token Index: 789

Text #11

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5932. Min Act: -0.0001

Data Index: 1429722 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5072. Min Act: -0.0001

Data Index: 1646954 (Python Code)

Max Activating Token Index: 776

Text #13

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.6376. Min Act: -0.0001

Data Index: 1412781 (Python Code)

Max Activating Token Index: 315

Text #14

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5321. Min Act: -0.0001

Data Index: 1488331 (Python Code)

Max Activating Token Index: 423

Text #15

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.4168. Min Act: -0.0001

Data Index: 1419116 (Python Code)

Max Activating Token Index: 737

Text #16

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.4588. Min Act: -0.0001

Data Index: 1482311 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5838. Min Act: -0.0001

Data Index: 1646882 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.4567. Min Act: -0.0001

Data Index: 1495272 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 2.1021. Min Range: -2.1021

Max Act: 1.5060. Min Act: -0.0001

Data Index: 1550608 (Python Code)

Max Activating Token Index: 208