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

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

Neuron 1607 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.8513. Min Act: -0.1700

Data Index: 1424543 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.8826. Min Act: -0.1700

Data Index: 1392470 (Python Code)

Max Activating Token Index: 500

Text #2

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.8201. Min Act: -0.1700

Data Index: 1482295 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6951. Min Act: -0.1700

Data Index: 1523521 (Python Code)

Max Activating Token Index: 436

Text #4

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.8201. Min Act: -0.1700

Data Index: 1614403 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6638. Min Act: -0.1700

Data Index: 1470225 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6638. Min Act: -0.1700

Data Index: 1612833 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.7263. Min Act: -0.1700

Data Index: 1631245 (Python Code)

Max Activating Token Index: 58

Text #8

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6951. Min Act: -0.1700

Data Index: 1576544 (Python Code)

Max Activating Token Index: 104

Text #9

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6638. Min Act: -0.1700

Data Index: 1656584 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6638. Min Act: -0.1700

Data Index: 1497866 (Python Code)

Max Activating Token Index: 57

Text #11

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6638. Min Act: -0.1700

Data Index: 1470952 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6326. Min Act: -0.1700

Data Index: 1540567 (Python Code)

Max Activating Token Index: 135

Text #13

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6013. Min Act: -0.1700

Data Index: 1498671 (Python Code)

Max Activating Token Index: 267

Text #14

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6326. Min Act: -0.1700

Data Index: 1454146 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6326. Min Act: -0.1700

Data Index: 1420289 (Python Code)

Max Activating Token Index: 596

Text #16

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6013. Min Act: -0.1700

Data Index: 1655291 (Python Code)

Max Activating Token Index: 160

Text #17

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.6326. Min Act: -0.1700

Data Index: 1484143 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.5701. Min Act: -0.1700

Data Index: 1400228 (Python Code)

Max Activating Token Index: 782

Text #19

Max Range: 5.8826. Min Range: -5.8826

Max Act: 5.5701. Min Act: -0.1700

Data Index: 1389566 (Python Code)

Max Activating Token Index: 89