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

Dataset: Open Web Text

Neuron 2073 in Layer 4

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: 3.7103. Min Range: -3.7103

Max Act: 3.7103. Min Act: -0.1700

Data Index: 8012541 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.6827. Min Act: -0.1700

Data Index: 7143342 (Open Web Text)

Max Activating Token Index: 897

Text #2

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.6786. Min Act: -0.1700

Data Index: 3502240 (Open Web Text)

Max Activating Token Index: 646

Text #3

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.6263. Min Act: -0.1700

Data Index: 6837032 (Open Web Text)

Max Activating Token Index: 540

Text #4

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.6284. Min Act: -0.1700

Data Index: 5146098 (Open Web Text)

Max Activating Token Index: 773

Text #5

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.6442. Min Act: -0.1700

Data Index: 4402534 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.6236. Min Act: -0.1700

Data Index: 3824688 (Open Web Text)

Max Activating Token Index: 911

Text #7

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.6133. Min Act: -0.1700

Data Index: 3569418 (Open Web Text)

Max Activating Token Index: 265

Text #8

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.6078. Min Act: -0.1700

Data Index: 1172018 (Open Web Text)

Max Activating Token Index: 511

Text #9

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5765. Min Act: -0.1700

Data Index: 1077035 (Open Web Text)

Max Activating Token Index: 581

Text #10

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5703. Min Act: -0.1700

Data Index: 552087 (Open Web Text)

Max Activating Token Index: 720

Text #11

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5790. Min Act: -0.1700

Data Index: 5438215 (Open Web Text)

Max Activating Token Index: 867

Text #12

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5790. Min Act: -0.1700

Data Index: 267796 (Open Web Text)

Max Activating Token Index: 391

Text #13

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5365. Min Act: -0.1700

Data Index: 3591128 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5515. Min Act: -0.1700

Data Index: 6027691 (Open Web Text)

Max Activating Token Index: 845

Text #15

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5428. Min Act: -0.1700

Data Index: 5101200 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5462. Min Act: -0.1700

Data Index: 7354855 (Open Web Text)

Max Activating Token Index: 899

Text #17

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5489. Min Act: -0.1700

Data Index: 2082987 (Open Web Text)

Max Activating Token Index: 254

Text #18

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5326. Min Act: -0.1700

Data Index: 3652838 (Open Web Text)

Max Activating Token Index: 666

Text #19

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.5578. Min Act: -0.1700

Data Index: 4294239 (Open Web Text)

Max Activating Token Index: 504