Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 628 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.3593. Min Act: -0.1700

Data Index: 1378995 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.2656. Min Act: -0.1700

Data Index: 1606002 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.2656. Min Act: -0.1700

Data Index: 1414911 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.2656. Min Act: -0.1700

Data Index: 1407120 (Python Code)

Max Activating Token Index: 220

Text #4

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.2656. Min Act: -0.1700

Data Index: 1506331 (Python Code)

Max Activating Token Index: 116

Text #5

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.1718. Min Act: -0.1700

Data Index: 1472451 (Python Code)

Max Activating Token Index: 329

Text #6

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.2343. Min Act: -0.1700

Data Index: 1612976 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.1718. Min Act: -0.1700

Data Index: 1523360 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.1249. Min Act: -0.1700

Data Index: 607157 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.1562. Min Act: -0.1700

Data Index: 1483352 (Python Code)

Max Activating Token Index: 232

Text #10

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.1718. Min Act: -0.1700

Data Index: 1623310 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.0781. Min Act: -0.1700

Data Index: 1382367 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.1249. Min Act: -0.1700

Data Index: 1558786 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.1093. Min Act: -0.1700

Data Index: 1527533 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.1249. Min Act: -0.1700

Data Index: 1461095 (Python Code)

Max Activating Token Index: 466

Text #15

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.0781. Min Act: -0.1700

Data Index: 1571857 (Python Code)

Max Activating Token Index: 217

Text #16

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.0781. Min Act: -0.1700

Data Index: 1629100 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.0624. Min Act: -0.1700

Data Index: 1557840 (Python Code)

Max Activating Token Index: 328

Text #18

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.1093. Min Act: -0.1700

Data Index: 1486561 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 5.3593. Min Range: -5.3593

Max Act: 5.0781. Min Act: -0.1700

Data Index: 1473492 (Python Code)

Max Activating Token Index: 337