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

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

Neuron 463 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: 3.3666. Min Range: -3.3666

Max Act: 3.3666. Min Act: -0.1700

Data Index: 370439 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.3509. Min Act: -0.1700

Data Index: 503355 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.3038. Min Act: -0.1700

Data Index: 670253 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2724. Min Act: -0.1700

Data Index: 1173922 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2566. Min Act: -0.1700

Data Index: 1167415 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2409. Min Act: -0.1700

Data Index: 873816 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2409. Min Act: -0.1700

Data Index: 23138 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2252. Min Act: -0.1700

Data Index: 539781 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2252. Min Act: -0.1700

Data Index: 1349937 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2252. Min Act: -0.1700

Data Index: 1014062 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1780. Min Act: -0.1700

Data Index: 643317 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1780. Min Act: -0.1700

Data Index: 604035 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1623. Min Act: -0.1700

Data Index: 1208566 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1465. Min Act: -0.1700

Data Index: 474979 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1937. Min Act: -0.1700

Data Index: 412043 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1937. Min Act: -0.1700

Data Index: 1308337 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1308. Min Act: -0.1700

Data Index: 1292582 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1465. Min Act: -0.1700

Data Index: 813093 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1623. Min Act: -0.1700

Data Index: 569834 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1780. Min Act: -0.1700

Data Index: 1143196 (C4 (Web Text))

Max Activating Token Index: 786