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

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

Neuron 124 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.9676. Min Act: -0.1700

Data Index: 102658 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.9051. Min Act: -0.1700

Data Index: 505181 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.8738. Min Act: -0.1700

Data Index: 711716 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.8426. Min Act: -0.1700

Data Index: 136667 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.8738. Min Act: -0.1700

Data Index: 310288 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.7800. Min Act: -0.1700

Data Index: 244355 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.8738. Min Act: -0.1700

Data Index: 1235120 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.8113. Min Act: -0.1700

Data Index: 228650 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.8426. Min Act: -0.1700

Data Index: 424380 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.8113. Min Act: -0.1699

Data Index: 688307 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.8426. Min Act: -0.1700

Data Index: 1121474 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.7800. Min Act: -0.1700

Data Index: 316457 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.7800. Min Act: -0.1700

Data Index: 445773 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.7487. Min Act: -0.1700

Data Index: 441302 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.8113. Min Act: -0.1700

Data Index: 245688 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.7487. Min Act: -0.1700

Data Index: 521599 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.7487. Min Act: -0.1700

Data Index: 781839 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.7174. Min Act: -0.1700

Data Index: 812188 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.7174. Min Act: -0.1700

Data Index: 746911 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 3.9676. Min Range: -3.9676

Max Act: 3.7174. Min Act: -0.1700

Data Index: 285212 (C4 (Web Text))

Max Activating Token Index: 622