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

Dataset: Open Web Text

Neuron 1925 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: 4.0494. Min Range: -4.0494

Max Act: 4.0494. Min Act: -0.1700

Data Index: 2929075 (Open Web Text)

Max Activating Token Index: 409

Text #1

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.9872. Min Act: -0.1700

Data Index: 3298307 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.9273. Min Act: -0.1700

Data Index: 2863608 (Open Web Text)

Max Activating Token Index: 607

Text #3

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.9311. Min Act: -0.1700

Data Index: 6830263 (Open Web Text)

Max Activating Token Index: 315

Text #4

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.8893. Min Act: -0.1700

Data Index: 8688998 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.7920. Min Act: -0.1700

Data Index: 8169850 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.8092. Min Act: -0.1700

Data Index: 4696733 (Open Web Text)

Max Activating Token Index: 457

Text #7

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.7439. Min Act: -0.1700

Data Index: 511901 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6940. Min Act: -0.1700

Data Index: 6379379 (Open Web Text)

Max Activating Token Index: 830

Text #9

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.7245. Min Act: -0.1700

Data Index: 926348 (Open Web Text)

Max Activating Token Index: 911

Text #10

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.7020. Min Act: -0.1700

Data Index: 3342227 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6475. Min Act: -0.1700

Data Index: 2872256 (Open Web Text)

Max Activating Token Index: 300

Text #12

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6500. Min Act: -0.1700

Data Index: 5492324 (Open Web Text)

Max Activating Token Index: 291

Text #13

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6247. Min Act: -0.1700

Data Index: 720162 (Open Web Text)

Max Activating Token Index: 918

Text #14

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6416. Min Act: -0.1700

Data Index: 6514467 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6667. Min Act: -0.1700

Data Index: 376813 (Open Web Text)

Max Activating Token Index: 996

Text #16

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6101. Min Act: -0.1700

Data Index: 927147 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6198. Min Act: -0.1700

Data Index: 5853112 (Open Web Text)

Max Activating Token Index: 292

Text #18

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6415. Min Act: -0.1700

Data Index: 4437490 (Open Web Text)

Max Activating Token Index: 362

Text #19

Max Range: 4.0494. Min Range: -4.0494

Max Act: 3.6528. Min Act: -0.1700

Data Index: 3962326 (Open Web Text)

Max Activating Token Index: 867