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

Dataset: Open Web Text

Neuron 919 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: 4.7078. Min Range: -4.7078

Max Act: 4.7078. Min Act: -0.1700

Data Index: 5101638 (Open Web Text)

Max Activating Token Index: 875

Text #1

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.6003. Min Act: -0.1700

Data Index: 587985 (Open Web Text)

Max Activating Token Index: 286

Text #2

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.5304. Min Act: -0.1700

Data Index: 4041412 (Open Web Text)

Max Activating Token Index: 609

Text #3

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4776. Min Act: -0.1700

Data Index: 5507512 (Open Web Text)

Max Activating Token Index: 784

Text #4

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.5228. Min Act: -0.1700

Data Index: 8597268 (Open Web Text)

Max Activating Token Index: 591

Text #5

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4240. Min Act: -0.1700

Data Index: 752592 (Open Web Text)

Max Activating Token Index: 837

Text #6

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4727. Min Act: -0.1700

Data Index: 7788901 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4275. Min Act: -0.1700

Data Index: 2243766 (Open Web Text)

Max Activating Token Index: 481

Text #8

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4136. Min Act: -0.1700

Data Index: 8479276 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4347. Min Act: -0.1700

Data Index: 469280 (Open Web Text)

Max Activating Token Index: 696

Text #10

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.3445. Min Act: -0.1700

Data Index: 7722740 (Open Web Text)

Max Activating Token Index: 537

Text #11

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.3924. Min Act: -0.1700

Data Index: 7041180 (Open Web Text)

Max Activating Token Index: 683

Text #12

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4055. Min Act: -0.1700

Data Index: 3944854 (Open Web Text)

Max Activating Token Index: 234

Text #13

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4140. Min Act: -0.1700

Data Index: 6747293 (Open Web Text)

Max Activating Token Index: 517

Text #14

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4023. Min Act: -0.1700

Data Index: 601194 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.3603. Min Act: -0.1700

Data Index: 3376700 (Open Web Text)

Max Activating Token Index: 979

Text #16

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4021. Min Act: -0.1700

Data Index: 6291191 (Open Web Text)

Max Activating Token Index: 555

Text #17

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4044. Min Act: -0.1700

Data Index: 2941813 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.4327. Min Act: -0.1700

Data Index: 3000596 (Open Web Text)

Max Activating Token Index: 819

Text #19

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.3754. Min Act: -0.1700

Data Index: 5805634 (Open Web Text)

Max Activating Token Index: 185