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

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

Neuron 1775 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: 7.1074. Min Range: -7.1074

Max Act: 7.0449. Min Act: -0.1700

Data Index: 523672 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 7.1074. Min Range: -7.1074

Max Act: 7.1074. Min Act: -0.1697

Data Index: 643865 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.7949. Min Act: -0.1699

Data Index: 963995 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.7636. Min Act: -0.1700

Data Index: 255500 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.7324. Min Act: -0.1700

Data Index: 1164247 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.7324. Min Act: -0.1697

Data Index: 1136324 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.7636. Min Act: -0.1700

Data Index: 515889 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.7324. Min Act: -0.1699

Data Index: 506154 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.7011. Min Act: -0.1698

Data Index: 354959 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.6074. Min Act: -0.1697

Data Index: 586355 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.5449. Min Act: -0.1700

Data Index: 427928 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.5761. Min Act: -0.1699

Data Index: 35449 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.5136. Min Act: -0.1699

Data Index: 1150119 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.4824. Min Act: -0.1699

Data Index: 82355 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.4511. Min Act: -0.1697

Data Index: 854042 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.4511. Min Act: -0.1697

Data Index: 85845 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.4199. Min Act: -0.1699

Data Index: 847434 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.4511. Min Act: -0.1700

Data Index: 863551 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.4511. Min Act: -0.1699

Data Index: 187666 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 7.1074. Min Range: -7.1074

Max Act: 6.3886. Min Act: -0.1697

Data Index: 1059931 (C4 (Web Text))

Max Activating Token Index: 880