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

Dataset: Open Web Text

Neuron 2695 in Layer 1

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: 3.8488. Min Range: -3.8488

Max Act: 3.8488. Min Act: -0.1700

Data Index: 705732 (Open Web Text)

Max Activating Token Index: 142

Text #1

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.8248. Min Act: -0.1700

Data Index: 830009 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.8025. Min Act: -0.1700

Data Index: 2812042 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7977. Min Act: -0.1700

Data Index: 2964364 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7767. Min Act: -0.1700

Data Index: 2355231 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7943. Min Act: -0.1700

Data Index: 3191853 (Open Web Text)

Max Activating Token Index: 461

Text #6

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7881. Min Act: -0.1700

Data Index: 2687050 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7734. Min Act: -0.1700

Data Index: 8615445 (Open Web Text)

Max Activating Token Index: 185

Text #8

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7592. Min Act: -0.1700

Data Index: 92880 (Open Web Text)

Max Activating Token Index: 186

Text #9

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7528. Min Act: -0.1700

Data Index: 882889 (Open Web Text)

Max Activating Token Index: 685

Text #10

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7605. Min Act: -0.1700

Data Index: 3966482 (Open Web Text)

Max Activating Token Index: 237

Text #11

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7551. Min Act: -0.1700

Data Index: 3855539 (Open Web Text)

Max Activating Token Index: 645

Text #12

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7724. Min Act: -0.1700

Data Index: 1291127 (Open Web Text)

Max Activating Token Index: 293

Text #13

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7533. Min Act: -0.1700

Data Index: 8238657 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7538. Min Act: -0.1700

Data Index: 6971351 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7645. Min Act: -0.1700

Data Index: 5755664 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7622. Min Act: -0.1700

Data Index: 2281604 (Open Web Text)

Max Activating Token Index: 259

Text #17

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7338. Min Act: -0.1700

Data Index: 1376123 (Open Web Text)

Max Activating Token Index: 264

Text #18

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7205. Min Act: -0.1700

Data Index: 4768581 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 3.8488. Min Range: -3.8488

Max Act: 3.7294. Min Act: -0.1700

Data Index: 2670508 (Open Web Text)

Max Activating Token Index: 426