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

Dataset: Open Web Text

Neuron 699 in Layer 3

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: 3.4572. Min Range: -3.4572

Max Act: 3.4572. Min Act: -0.1700

Data Index: 6809401 (Open Web Text)

Max Activating Token Index: 95

Text #1

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.3758. Min Act: -0.1700

Data Index: 6270980 (Open Web Text)

Max Activating Token Index: 535

Text #2

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.3339. Min Act: -0.1700

Data Index: 7320848 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.3551. Min Act: -0.1700

Data Index: 5412996 (Open Web Text)

Max Activating Token Index: 100

Text #4

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.3142. Min Act: -0.1700

Data Index: 2329632 (Open Web Text)

Max Activating Token Index: 939

Text #5

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.3298. Min Act: -0.1700

Data Index: 7861910 (Open Web Text)

Max Activating Token Index: 445

Text #6

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.3237. Min Act: -0.1700

Data Index: 2292382 (Open Web Text)

Max Activating Token Index: 234

Text #7

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2995. Min Act: -0.1700

Data Index: 6529186 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2950. Min Act: -0.1700

Data Index: 3255487 (Open Web Text)

Max Activating Token Index: 680

Text #9

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.3198. Min Act: -0.1700

Data Index: 1186542 (Open Web Text)

Max Activating Token Index: 499

Text #10

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2917. Min Act: -0.1700

Data Index: 2126545 (Open Web Text)

Max Activating Token Index: 604

Text #11

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2643. Min Act: -0.1700

Data Index: 7481462 (Open Web Text)

Max Activating Token Index: 893

Text #12

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2584. Min Act: -0.1700

Data Index: 2001694 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2616. Min Act: -0.1700

Data Index: 4519656 (Open Web Text)

Max Activating Token Index: 120

Text #14

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2679. Min Act: -0.1700

Data Index: 1259608 (Open Web Text)

Max Activating Token Index: 640

Text #15

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2596. Min Act: -0.1700

Data Index: 4954542 (Open Web Text)

Max Activating Token Index: 93

Text #16

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2608. Min Act: -0.1700

Data Index: 2243422 (Open Web Text)

Max Activating Token Index: 891

Text #17

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2568. Min Act: -0.1700

Data Index: 1174008 (Open Web Text)

Max Activating Token Index: 401

Text #18

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2656. Min Act: -0.1700

Data Index: 733098 (Open Web Text)

Max Activating Token Index: 620

Text #19

Max Range: 3.4572. Min Range: -3.4572

Max Act: 3.2622. Min Act: -0.1700

Data Index: 7420190 (Open Web Text)

Max Activating Token Index: 207