Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1728 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.4391. Min Act: -0.1700

Data Index: 1392772 (Python Code)

Max Activating Token Index: 849

Text #1

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.4078. Min Act: -0.1700

Data Index: 1549612 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.4235. Min Act: -0.1700

Data Index: 1475853 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.4078. Min Act: -0.1700

Data Index: 1623828 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.3764. Min Act: -0.1700

Data Index: 1581845 (Python Code)

Max Activating Token Index: 433

Text #5

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2979. Min Act: -0.1700

Data Index: 1585387 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.3450. Min Act: -0.1700

Data Index: 1587306 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.3450. Min Act: -0.1700

Data Index: 1601811 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.3293. Min Act: -0.1700

Data Index: 1386297 (Python Code)

Max Activating Token Index: 78

Text #9

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.3293. Min Act: -0.1700

Data Index: 1541479 (Python Code)

Max Activating Token Index: 876

Text #10

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2979. Min Act: -0.1700

Data Index: 1462234 (Python Code)

Max Activating Token Index: 236

Text #11

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2979. Min Act: -0.1700

Data Index: 1626090 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2979. Min Act: -0.1700

Data Index: 1551358 (Python Code)

Max Activating Token Index: 923

Text #13

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2979. Min Act: -0.1700

Data Index: 1478909 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.3136. Min Act: -0.1700

Data Index: 1425872 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2822. Min Act: -0.1700

Data Index: 1472710 (Python Code)

Max Activating Token Index: 664

Text #16

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2979. Min Act: -0.1700

Data Index: 1553228 (Python Code)

Max Activating Token Index: 754

Text #17

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2665. Min Act: -0.1700

Data Index: 1507871 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2665. Min Act: -0.1700

Data Index: 1565937 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 3.4391. Min Range: -3.4391

Max Act: 3.2822. Min Act: -0.1700

Data Index: 1534580 (Python Code)

Max Activating Token Index: 43