Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 990 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.9245. Min Act: -0.1700

Data Index: 1022429 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8933. Min Act: -0.1700

Data Index: 1176649 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.9245. Min Act: -0.1700

Data Index: 10257 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8620. Min Act: -0.1700

Data Index: 268802 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8308. Min Act: -0.1700

Data Index: 188702 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8620. Min Act: -0.1700

Data Index: 674183 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8620. Min Act: -0.1700

Data Index: 749461 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.7995. Min Act: -0.1700

Data Index: 1012399 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8620. Min Act: -0.1700

Data Index: 235929 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8620. Min Act: -0.1700

Data Index: 130250 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.7683. Min Act: -0.1700

Data Index: 509272 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8620. Min Act: -0.1700

Data Index: 1142636 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.7995. Min Act: -0.1700

Data Index: 316821 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.7683. Min Act: -0.1700

Data Index: 909636 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8308. Min Act: -0.1700

Data Index: 1319325 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.7995. Min Act: -0.1700

Data Index: 1341658 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.8620. Min Act: -0.1700

Data Index: 1010658 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.7995. Min Act: -0.1700

Data Index: 567306 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.7683. Min Act: -0.1700

Data Index: 808624 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 5.9245. Min Range: -5.9245

Max Act: 5.7995. Min Act: -0.1700

Data Index: 684248 (C4 (Web Text))

Max Activating Token Index: 784