Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 814 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0133. Min Range: -5.0133

Max Act: 5.0133. Min Act: -0.1700

Data Index: 1561044 (Python Code)

Max Activating Token Index: 588

Text #1

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.9196. Min Act: -0.1700

Data Index: 1526764 (Python Code)

Max Activating Token Index: 845

Text #2

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.8258. Min Act: -0.1700

Data Index: 1456553 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.7946. Min Act: -0.1700

Data Index: 1464456 (Python Code)

Max Activating Token Index: 509

Text #4

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.7633. Min Act: -0.1700

Data Index: 1633783 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.7633. Min Act: -0.1700

Data Index: 1585966 (Python Code)

Max Activating Token Index: 401

Text #6

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.7321. Min Act: -0.1700

Data Index: 1508369 (Python Code)

Max Activating Token Index: 910

Text #7

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.7008. Min Act: -0.1700

Data Index: 1563653 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.7008. Min Act: -0.1700

Data Index: 1370430 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.6696. Min Act: -0.1700

Data Index: 1442909 (Python Code)

Max Activating Token Index: 430

Text #10

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.7008. Min Act: -0.1700

Data Index: 1472174 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.6071. Min Act: -0.1699

Data Index: 1612163 (Python Code)

Max Activating Token Index: 478

Text #12

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.6696. Min Act: -0.1700

Data Index: 1609571 (Python Code)

Max Activating Token Index: 560

Text #13

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.6383. Min Act: -0.1700

Data Index: 1377976 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.6696. Min Act: -0.1700

Data Index: 1404889 (Python Code)

Max Activating Token Index: 453

Text #15

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.7008. Min Act: -0.1700

Data Index: 1503518 (Python Code)

Max Activating Token Index: 377

Text #16

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.6383. Min Act: -0.1700

Data Index: 1523525 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.6383. Min Act: -0.1700

Data Index: 1386299 (Python Code)

Max Activating Token Index: 487

Text #18

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.6071. Min Act: -0.1700

Data Index: 1498913 (Python Code)

Max Activating Token Index: 455

Text #19

Max Range: 5.0133. Min Range: -5.0133

Max Act: 4.6696. Min Act: -0.1700

Data Index: 1549433 (Python Code)

Max Activating Token Index: 452