Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 546 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.2795. Min Act: -0.1700

Data Index: 10203 (Open Web Text)

Max Activating Token Index: 985

Text #1

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.2872. Min Act: -0.1700

Data Index: 7929793 (Open Web Text)

Max Activating Token Index: 576

Text #2

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.2426. Min Act: -0.1700

Data Index: 3963484 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.1989. Min Act: -0.1700

Data Index: 7399858 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.1524. Min Act: -0.1700

Data Index: 4427848 (Open Web Text)

Max Activating Token Index: 952

Text #5

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.2243. Min Act: -0.1700

Data Index: 8324446 (Open Web Text)

Max Activating Token Index: 852

Text #6

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.1638. Min Act: -0.1700

Data Index: 5578899 (Open Web Text)

Max Activating Token Index: 717

Text #7

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.1787. Min Act: -0.1700

Data Index: 799933 (Open Web Text)

Max Activating Token Index: 300

Text #8

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.1471. Min Act: -0.1700

Data Index: 5341756 (Open Web Text)

Max Activating Token Index: 435

Text #9

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.1727. Min Act: -0.1700

Data Index: 6944977 (Open Web Text)

Max Activating Token Index: 661

Text #10

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0935. Min Act: -0.1700

Data Index: 5139112 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0698. Min Act: -0.1700

Data Index: 298715 (Open Web Text)

Max Activating Token Index: 778

Text #12

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0903. Min Act: -0.1700

Data Index: 8495190 (Open Web Text)

Max Activating Token Index: 909

Text #13

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0537. Min Act: -0.1700

Data Index: 3536054 (Open Web Text)

Max Activating Token Index: 869

Text #14

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0584. Min Act: -0.1700

Data Index: 2692896 (Open Web Text)

Max Activating Token Index: 916

Text #15

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0610. Min Act: -0.1700

Data Index: 6240689 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0626. Min Act: -0.1700

Data Index: 5101912 (Open Web Text)

Max Activating Token Index: 938

Text #17

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0791. Min Act: -0.1700

Data Index: 8221114 (Open Web Text)

Max Activating Token Index: 93

Text #18

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0688. Min Act: -0.1700

Data Index: 6493834 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 4.2872. Min Range: -4.2872

Max Act: 4.0067. Min Act: -0.1700

Data Index: 5310355 (Open Web Text)

Max Activating Token Index: 449