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

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

Neuron 1957 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: 3.1613. Min Range: -3.1613

Max Act: 3.1613. Min Act: -0.1700

Data Index: 1393437 (Python Code)

Max Activating Token Index: 322

Text #1

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.1613. Min Act: -0.1700

Data Index: 1385125 (Python Code)

Max Activating Token Index: 304

Text #2

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.1298. Min Act: -0.1700

Data Index: 1487738 (Python Code)

Max Activating Token Index: 79

Text #3

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.1140. Min Act: -0.1700

Data Index: 1546967 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.1140. Min Act: -0.1700

Data Index: 1444800 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0982. Min Act: -0.1700

Data Index: 1435887 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0982. Min Act: -0.1700

Data Index: 1522527 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0982. Min Act: -0.1700

Data Index: 1414197 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0825. Min Act: -0.1700

Data Index: 1562329 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0667. Min Act: -0.1700

Data Index: 1421361 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0825. Min Act: -0.1700

Data Index: 1646345 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0825. Min Act: -0.1700

Data Index: 1533392 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0667. Min Act: -0.1700

Data Index: 1645117 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0825. Min Act: -0.1699

Data Index: 1388325 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0667. Min Act: -0.1700

Data Index: 1593586 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0509. Min Act: -0.1700

Data Index: 1430107 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0667. Min Act: -0.1700

Data Index: 1446370 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0667. Min Act: -0.1700

Data Index: 1553323 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0509. Min Act: -0.1700

Data Index: 1623495 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 3.1613. Min Range: -3.1613

Max Act: 3.0351. Min Act: -0.1700

Data Index: 1498714 (Python Code)

Max Activating Token Index: 14