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

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

Neuron 1393 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: 3.7436. Min Range: -3.7436

Max Act: 3.7436. Min Act: -0.1700

Data Index: 499090 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.7123. Min Act: -0.1700

Data Index: 1093634 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.7123. Min Act: -0.1700

Data Index: 1162571 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.7123. Min Act: -0.1700

Data Index: 460977 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.6498. Min Act: -0.1700

Data Index: 1161262 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.6811. Min Act: -0.1700

Data Index: 628896 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.6498. Min Act: -0.1700

Data Index: 81773 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.6498. Min Act: -0.1700

Data Index: 1160251 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.6184. Min Act: -0.1700

Data Index: 14412 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.6498. Min Act: -0.1700

Data Index: 1281983 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.6184. Min Act: -0.1700

Data Index: 1288855 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.6184. Min Act: -0.1700

Data Index: 1039778 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.5871. Min Act: -0.1700

Data Index: 940084 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.6184. Min Act: -0.1700

Data Index: 44020 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.5871. Min Act: -0.1700

Data Index: 1233596 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.5871. Min Act: -0.1700

Data Index: 1209443 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.5871. Min Act: -0.1700

Data Index: 166347 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.5558. Min Act: -0.1700

Data Index: 572825 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.5871. Min Act: -0.1700

Data Index: 921685 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 3.7436. Min Range: -3.7436

Max Act: 3.4931. Min Act: -0.1700

Data Index: 896031 (C4 (Web Text))

Max Activating Token Index: 258