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

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

Neuron 180 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: 5.5840. Min Range: -5.5840

Max Act: 5.5840. Min Act: -0.1700

Data Index: 649734 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.4590. Min Act: -0.1700

Data Index: 923998 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.4902. Min Act: -0.1700

Data Index: 911034 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.4902. Min Act: -0.1700

Data Index: 1103103 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.4277. Min Act: -0.1700

Data Index: 110826 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3965. Min Act: -0.1700

Data Index: 1236999 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3652. Min Act: -0.1699

Data Index: 347145 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3340. Min Act: -0.1700

Data Index: 841910 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3340. Min Act: -0.1700

Data Index: 35349 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3965. Min Act: -0.1700

Data Index: 233489 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3652. Min Act: -0.1700

Data Index: 1121184 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3027. Min Act: -0.1700

Data Index: 677739 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3027. Min Act: -0.1700

Data Index: 612831 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.2402. Min Act: -0.1699

Data Index: 1095002 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3027. Min Act: -0.1700

Data Index: 826672 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3027. Min Act: -0.1700

Data Index: 742317 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.2715. Min Act: -0.1700

Data Index: 188183 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.3027. Min Act: -0.1700

Data Index: 1016313 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.2402. Min Act: -0.1700

Data Index: 229211 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 5.5840. Min Range: -5.5840

Max Act: 5.2402. Min Act: -0.1700

Data Index: 507235 (C4 (Web Text))

Max Activating Token Index: 939