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

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

Neuron 220 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: 3.9919. Min Range: -3.9919

Max Act: 3.9606. Min Act: -0.1700

Data Index: 375957 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 275608 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 586109 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 116031 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 320547 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 287418 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9919. Min Act: -0.1700

Data Index: 1179126 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 1281300 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 36624 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9606. Min Act: -0.1700

Data Index: 998333 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.8981. Min Act: -0.1700

Data Index: 1047485 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.8981. Min Act: -0.1700

Data Index: 822694 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.8981. Min Act: -0.1700

Data Index: 602718 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 1118115 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.8981. Min Act: -0.1700

Data Index: 1196921 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 255710 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.8981. Min Act: -0.1700

Data Index: 302154 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.8981. Min Act: -0.1700

Data Index: 646452 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.9294. Min Act: -0.1700

Data Index: 749039 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 3.9919. Min Range: -3.9919

Max Act: 3.8668. Min Act: -0.1700

Data Index: 675014 (C4 (Web Text))

Max Activating Token Index: 904