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

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

Neuron 321 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: 3.7522. Min Range: -3.7522

Max Act: 3.7522. Min Act: -0.1700

Data Index: 359611 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.7209. Min Act: -0.1700

Data Index: 1162780 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.7209. Min Act: -0.1700

Data Index: 716687 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.7209. Min Act: -0.1700

Data Index: 524348 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6896. Min Act: -0.1700

Data Index: 44504 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6583. Min Act: -0.1700

Data Index: 1181261 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6896. Min Act: -0.1700

Data Index: 295487 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6583. Min Act: -0.1700

Data Index: 814065 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6270. Min Act: -0.1700

Data Index: 63524 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6270. Min Act: -0.1700

Data Index: 945867 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6583. Min Act: -0.1700

Data Index: 390 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 494619 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1349844 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 566326 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 310686 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1207188 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6270. Min Act: -0.1700

Data Index: 1219929 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5644. Min Act: -0.1700

Data Index: 250912 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1262475 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6583. Min Act: -0.1700

Data Index: 564972 (C4 (Web Text))

Max Activating Token Index: 1022