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

Dataset: Open Web Text

Neuron 2751 in Layer 2

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: 4.5626. Min Range: -4.5626

Max Act: 4.5211. Min Act: -0.1700

Data Index: 7239028 (Open Web Text)

Max Activating Token Index: 474

Text #1

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.5626. Min Act: -0.1700

Data Index: 6582292 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.4714. Min Act: -0.1700

Data Index: 6578382 (Open Web Text)

Max Activating Token Index: 288

Text #3

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.4264. Min Act: -0.1700

Data Index: 1754608 (Open Web Text)

Max Activating Token Index: 415

Text #4

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.4057. Min Act: -0.1700

Data Index: 908560 (Open Web Text)

Max Activating Token Index: 860

Text #5

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.4031. Min Act: -0.1700

Data Index: 304339 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.3582. Min Act: -0.1700

Data Index: 1896544 (Open Web Text)

Max Activating Token Index: 64

Text #7

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2872. Min Act: -0.1700

Data Index: 1758171 (Open Web Text)

Max Activating Token Index: 830

Text #8

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2940. Min Act: -0.1700

Data Index: 6422395 (Open Web Text)

Max Activating Token Index: 679

Text #9

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2707. Min Act: -0.1700

Data Index: 5992257 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2875. Min Act: -0.1700

Data Index: 8754157 (Open Web Text)

Max Activating Token Index: 777

Text #11

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.3356. Min Act: -0.1700

Data Index: 664362 (Open Web Text)

Max Activating Token Index: 290

Text #12

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2331. Min Act: -0.1700

Data Index: 6909145 (Open Web Text)

Max Activating Token Index: 233

Text #13

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2666. Min Act: -0.1700

Data Index: 1840162 (Open Web Text)

Max Activating Token Index: 259

Text #14

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2965. Min Act: -0.1700

Data Index: 733763 (Open Web Text)

Max Activating Token Index: 462

Text #15

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2980. Min Act: -0.1700

Data Index: 6494717 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2762. Min Act: -0.1700

Data Index: 7748998 (Open Web Text)

Max Activating Token Index: 519

Text #17

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2508. Min Act: -0.1700

Data Index: 2893284 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2348. Min Act: -0.1700

Data Index: 6891265 (Open Web Text)

Max Activating Token Index: 592

Text #19

Max Range: 4.5626. Min Range: -4.5626

Max Act: 4.2897. Min Act: -0.1700

Data Index: 1315508 (Open Web Text)

Max Activating Token Index: 138