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

Dataset: Open Web Text

Neuron 2994 in Layer 6

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: 4.1880. Min Range: -4.1880

Max Act: 4.1880. Min Act: -0.1700

Data Index: 8202241 (Open Web Text)

Max Activating Token Index: 835

Text #1

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0780. Min Act: -0.1700

Data Index: 7722601 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0594. Min Act: -0.1700

Data Index: 1104604 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0196. Min Act: -0.1700

Data Index: 1231345 (Open Web Text)

Max Activating Token Index: 821

Text #4

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.9921. Min Act: -0.1700

Data Index: 8651876 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0085. Min Act: -0.1700

Data Index: 8543463 (Open Web Text)

Max Activating Token Index: 466

Text #6

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.9610. Min Act: -0.1700

Data Index: 6987 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.9355. Min Act: -0.1700

Data Index: 189009 (Open Web Text)

Max Activating Token Index: 265

Text #8

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.9388. Min Act: -0.1700

Data Index: 6887552 (Open Web Text)

Max Activating Token Index: 993

Text #9

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8823. Min Act: -0.1700

Data Index: 2737737 (Open Web Text)

Max Activating Token Index: 675

Text #10

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8698. Min Act: -0.1700

Data Index: 4775029 (Open Web Text)

Max Activating Token Index: 586

Text #11

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8690. Min Act: -0.1700

Data Index: 2840996 (Open Web Text)

Max Activating Token Index: 216

Text #12

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8831. Min Act: -0.1700

Data Index: 7107265 (Open Web Text)

Max Activating Token Index: 978

Text #13

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8420. Min Act: -0.1700

Data Index: 3415252 (Open Web Text)

Max Activating Token Index: 378

Text #14

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8532. Min Act: -0.1700

Data Index: 2266056 (Open Web Text)

Max Activating Token Index: 462

Text #15

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8647. Min Act: -0.1700

Data Index: 5843467 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8328. Min Act: -0.1700

Data Index: 398847 (Open Web Text)

Max Activating Token Index: 794

Text #17

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8525. Min Act: -0.1700

Data Index: 6849351 (Open Web Text)

Max Activating Token Index: 77

Text #18

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8586. Min Act: -0.1700

Data Index: 5569584 (Open Web Text)

Max Activating Token Index: 251

Text #19

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.8660. Min Act: -0.1700

Data Index: 8071026 (Open Web Text)

Max Activating Token Index: 373