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

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

Neuron 170 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: 3.3992. Min Range: -3.3992

Max Act: 3.3992. Min Act: -0.1700

Data Index: 1524440 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.3207. Min Act: -0.1700

Data Index: 1577944 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.3521. Min Act: -0.1700

Data Index: 1406422 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.3207. Min Act: -0.1700

Data Index: 1560797 (Python Code)

Max Activating Token Index: 686

Text #4

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2893. Min Act: -0.1700

Data Index: 1602258 (Python Code)

Max Activating Token Index: 474

Text #5

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.3050. Min Act: -0.1700

Data Index: 1631775 (Python Code)

Max Activating Token Index: 645

Text #6

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2736. Min Act: -0.1700

Data Index: 1602262 (Python Code)

Max Activating Token Index: 207

Text #7

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2736. Min Act: -0.1700

Data Index: 1403927 (Python Code)

Max Activating Token Index: 316

Text #8

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2579. Min Act: -0.1700

Data Index: 1546662 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2736. Min Act: -0.1700

Data Index: 1549525 (Python Code)

Max Activating Token Index: 549

Text #10

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2264. Min Act: -0.1700

Data Index: 1505836 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2264. Min Act: -0.1700

Data Index: 1467209 (Python Code)

Max Activating Token Index: 844

Text #12

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2264. Min Act: -0.1700

Data Index: 1477820 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2264. Min Act: -0.1700

Data Index: 1643415 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2107. Min Act: -0.1700

Data Index: 1437921 (Python Code)

Max Activating Token Index: 91

Text #15

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2107. Min Act: -0.1700

Data Index: 1614839 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2264. Min Act: -0.1700

Data Index: 1600778 (Python Code)

Max Activating Token Index: 566

Text #17

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1792. Min Act: -0.1700

Data Index: 1568869 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2107. Min Act: -0.1700

Data Index: 1280788 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1792. Min Act: -0.1700

Data Index: 1377005 (Python Code)

Max Activating Token Index: 82