Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 537 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.8530. Min Act: -0.1700

Data Index: 1514949 (Python Code)

Max Activating Token Index: 976

Text #1

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.8217. Min Act: -0.1700

Data Index: 1640286 (Python Code)

Max Activating Token Index: 1008

Text #2

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.8530. Min Act: -0.1700

Data Index: 1438315 (Python Code)

Max Activating Token Index: 123

Text #3

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.8530. Min Act: -0.1700

Data Index: 1461848 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.8842. Min Act: -0.1700

Data Index: 1606565 (Python Code)

Max Activating Token Index: 469

Text #5

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.8217. Min Act: -0.1700

Data Index: 1426975 (Python Code)

Max Activating Token Index: 344

Text #6

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.8842. Min Act: -0.1700

Data Index: 1603570 (Python Code)

Max Activating Token Index: 867

Text #7

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7278. Min Act: -0.1700

Data Index: 1536154 (Python Code)

Max Activating Token Index: 709

Text #8

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7591. Min Act: -0.1700

Data Index: 1539051 (Python Code)

Max Activating Token Index: 683

Text #9

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7591. Min Act: -0.1700

Data Index: 1424323 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.6965. Min Act: -0.1700

Data Index: 1629734 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7591. Min Act: -0.1700

Data Index: 1506365 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7904. Min Act: -0.1700

Data Index: 1553740 (Python Code)

Max Activating Token Index: 117

Text #13

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7904. Min Act: -0.1700

Data Index: 1364378 (Python Code)

Max Activating Token Index: 948

Text #14

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7591. Min Act: -0.1700

Data Index: 1481491 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7904. Min Act: -0.1700

Data Index: 1441538 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7278. Min Act: -0.1700

Data Index: 1396729 (Python Code)

Max Activating Token Index: 697

Text #17

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7591. Min Act: -0.1700

Data Index: 1599918 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7591. Min Act: -0.1700

Data Index: 1591771 (Python Code)

Max Activating Token Index: 618

Text #19

Max Range: 3.8842. Min Range: -3.8842

Max Act: 3.7278. Min Act: -0.1700

Data Index: 1438893 (Python Code)

Max Activating Token Index: 894