Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 2035 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1509. Min Range: -4.1509

Max Act: 4.1509. Min Act: -0.1700

Data Index: 1626185 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 4.1509. Min Range: -4.1509

Max Act: 4.0725. Min Act: -0.1700

Data Index: 1639878 (Python Code)

Max Activating Token Index: 358

Text #2

Max Range: 4.1509. Min Range: -4.1509

Max Act: 4.0812. Min Act: -0.1700

Data Index: 1532554 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.9305. Min Act: -0.1700

Data Index: 1549172 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.9325. Min Act: -0.1700

Data Index: 1616016 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.9354. Min Act: -0.1700

Data Index: 1509474 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.9115. Min Act: -0.1700

Data Index: 1374647 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.8665. Min Act: -0.1700

Data Index: 1656688 (Python Code)

Max Activating Token Index: 130

Text #8

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.8770. Min Act: -0.1700

Data Index: 1591946 (Python Code)

Max Activating Token Index: 57

Text #9

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.8590. Min Act: -0.1700

Data Index: 1555611 (Python Code)

Max Activating Token Index: 394

Text #10

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.8512. Min Act: -0.1700

Data Index: 1581495 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.8397. Min Act: -0.1700

Data Index: 1614006 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.8088. Min Act: -0.1700

Data Index: 1514818 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1647109 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1653686 (Python Code)

Max Activating Token Index: 807

Text #15

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.7962. Min Act: -0.1700

Data Index: 1485731 (Python Code)

Max Activating Token Index: 896

Text #16

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.7951. Min Act: -0.1700

Data Index: 1515915 (Python Code)

Max Activating Token Index: 147

Text #17

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.8051. Min Act: -0.1700

Data Index: 1648196 (Python Code)

Max Activating Token Index: 928

Text #18

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.7963. Min Act: -0.1700

Data Index: 1591658 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 4.1509. Min Range: -4.1509

Max Act: 3.7775. Min Act: -0.1700

Data Index: 1589350 (Python Code)

Max Activating Token Index: 799