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

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

Neuron 225 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3936. Min Act: -0.1700

Data Index: 1123985 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3936. Min Act: -0.1697

Data Index: 669787 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3779. Min Act: -0.1699

Data Index: 396763 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3936. Min Act: -0.1700

Data Index: 497954 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3623. Min Act: -0.1700

Data Index: 610273 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3623. Min Act: -0.1700

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3466. Min Act: -0.1700

Data Index: 289307 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3309. Min Act: -0.1700

Data Index: 544625 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3466. Min Act: -0.1700

Data Index: 545327 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3309. Min Act: -0.1699

Data Index: 1122428 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3309. Min Act: -0.1700

Data Index: 409373 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3309. Min Act: -0.1700

Data Index: 930753 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3152. Min Act: -0.1700

Data Index: 30403 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3309. Min Act: -0.1700

Data Index: 1224387 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.2995. Min Act: -0.1700

Data Index: 93958 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.2995. Min Act: -0.1700

Data Index: 377208 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.2995. Min Act: -0.1698

Data Index: 393084 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3309. Min Act: -0.1700

Data Index: 1150808 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.2995. Min Act: -0.1700

Data Index: 824007 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.3936. Min Range: -3.3936

Max Act: 3.3309. Min Act: -0.1700

Data Index: 358601 (C4 (Web Text))

Max Activating Token Index: 768