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

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

Neuron 302 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: 3.6983. Min Range: -3.6983

Max Act: 3.6983. Min Act: -0.1700

Data Index: 730865 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.5731. Min Act: -0.1700

Data Index: 1300833 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.6357. Min Act: -0.1700

Data Index: 909817 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.5418. Min Act: -0.1700

Data Index: 812349 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.5104. Min Act: -0.1700

Data Index: 39841 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.5104. Min Act: -0.1700

Data Index: 790373 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.5418. Min Act: -0.1700

Data Index: 208680 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4791. Min Act: -0.1700

Data Index: 677538 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.5104. Min Act: -0.1700

Data Index: 1304829 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.5418. Min Act: -0.1700

Data Index: 15109 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4791. Min Act: -0.1700

Data Index: 97878 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1340583 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4164. Min Act: -0.1700

Data Index: 1027043 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4477. Min Act: -0.1700

Data Index: 776523 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4477. Min Act: -0.1700

Data Index: 30581 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4164. Min Act: -0.1700

Data Index: 684484 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.3850. Min Act: -0.1700

Data Index: 491044 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4164. Min Act: -0.1700

Data Index: 1055623 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4164. Min Act: -0.1700

Data Index: 1148800 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 3.6983. Min Range: -3.6983

Max Act: 3.4164. Min Act: -0.1700

Data Index: 789056 (C4 (Web Text))

Max Activating Token Index: 839