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

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

Neuron 1786 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.3100. Min Act: -0.1700

Data Index: 1069068 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.1999. Min Act: -0.1700

Data Index: 668297 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.1999. Min Act: -0.1700

Data Index: 184492 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.1370. Min Act: -0.1700

Data Index: 718692 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.1527. Min Act: -0.1700

Data Index: 755245 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.1212. Min Act: -0.1700

Data Index: 1105142 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.0739. Min Act: -0.1700

Data Index: 540763 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.0739. Min Act: -0.1700

Data Index: 1250542 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.0581. Min Act: -0.1700

Data Index: 351846 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.0265. Min Act: -0.1700

Data Index: 1227535 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.0265. Min Act: -0.1700

Data Index: 464939 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 3.3100. Min Range: -3.3100

Max Act: 2.9633. Min Act: -0.1700

Data Index: 89292 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.0265. Min Act: -0.1700

Data Index: 104729 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 3.3100. Min Range: -3.3100

Max Act: 2.9791. Min Act: -0.1700

Data Index: 1327974 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.0423. Min Act: -0.1700

Data Index: 1350410 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.0265. Min Act: -0.1700

Data Index: 1006130 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 3.3100. Min Range: -3.3100

Max Act: 2.9949. Min Act: -0.1700

Data Index: 1249687 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 3.3100. Min Range: -3.3100

Max Act: 2.9791. Min Act: -0.1700

Data Index: 1214612 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 3.3100. Min Range: -3.3100

Max Act: 3.0265. Min Act: -0.1700

Data Index: 520526 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 3.3100. Min Range: -3.3100

Max Act: 2.9949. Min Act: -0.1700

Data Index: 154203 (C4 (Web Text))

Max Activating Token Index: 639