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

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

Neuron 642 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.9147. Min Act: -0.1700

Data Index: 893257 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.9772. Min Act: -0.1700

Data Index: 753854 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8834. Min Act: -0.1700

Data Index: 316350 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8834. Min Act: -0.1700

Data Index: 1284651 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8834. Min Act: -0.1700

Data Index: 676470 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8521. Min Act: -0.1700

Data Index: 414529 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8521. Min Act: -0.1700

Data Index: 334226 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8521. Min Act: -0.1700

Data Index: 1115392 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8521. Min Act: -0.1700

Data Index: 1032921 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8209. Min Act: -0.1700

Data Index: 814279 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8521. Min Act: -0.1700

Data Index: 580984 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8209. Min Act: -0.1700

Data Index: 314105 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8209. Min Act: -0.1700

Data Index: 1118375 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.8209. Min Act: -0.1700

Data Index: 160283 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.7583. Min Act: -0.1700

Data Index: 1029680 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.7583. Min Act: -0.1700

Data Index: 1170582 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.7896. Min Act: -0.1700

Data Index: 314238 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.7583. Min Act: -0.1700

Data Index: 739123 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.7270. Min Act: -0.1700

Data Index: 528897 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 3.9772. Min Range: -3.9772

Max Act: 3.7583. Min Act: -0.1700

Data Index: 935931 (C4 (Web Text))

Max Activating Token Index: 4