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

Dataset: Open Web Text

Neuron 736 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: 5.4650. Min Range: -5.4650

Max Act: 5.4650. Min Act: -0.1700

Data Index: 5193770 (Open Web Text)

Max Activating Token Index: 216

Text #1

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.3486. Min Act: -0.1700

Data Index: 8155623 (Open Web Text)

Max Activating Token Index: 124

Text #2

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.3229. Min Act: -0.1700

Data Index: 5453435 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.3031. Min Act: -0.1700

Data Index: 1074117 (Open Web Text)

Max Activating Token Index: 528

Text #4

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.3038. Min Act: -0.1700

Data Index: 2102578 (Open Web Text)

Max Activating Token Index: 679

Text #5

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.3182. Min Act: -0.1700

Data Index: 1699294 (Open Web Text)

Max Activating Token Index: 670

Text #6

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.3024. Min Act: -0.1700

Data Index: 4621204 (Open Web Text)

Max Activating Token Index: 726

Text #7

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2930. Min Act: -0.1700

Data Index: 6884635 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2864. Min Act: -0.1700

Data Index: 4574411 (Open Web Text)

Max Activating Token Index: 571

Text #9

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2989. Min Act: -0.1700

Data Index: 3089290 (Open Web Text)

Max Activating Token Index: 333

Text #10

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2769. Min Act: -0.1700

Data Index: 7643917 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2833. Min Act: -0.1700

Data Index: 8640930 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2643. Min Act: -0.1700

Data Index: 1808988 (Open Web Text)

Max Activating Token Index: 725

Text #13

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2734. Min Act: -0.1700

Data Index: 8580750 (Open Web Text)

Max Activating Token Index: 270

Text #14

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2648. Min Act: -0.1700

Data Index: 6230969 (Open Web Text)

Max Activating Token Index: 395

Text #15

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2353. Min Act: -0.1700

Data Index: 5713283 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2439. Min Act: -0.1700

Data Index: 93511 (Open Web Text)

Max Activating Token Index: 506

Text #17

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2561. Min Act: -0.1700

Data Index: 1920767 (Open Web Text)

Max Activating Token Index: 591

Text #18

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2830. Min Act: -0.1700

Data Index: 4461274 (Open Web Text)

Max Activating Token Index: 619

Text #19

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2132. Min Act: -0.1700

Data Index: 2983765 (Open Web Text)

Max Activating Token Index: 344