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

Dataset: Open Web Text

Neuron 1437 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: 4.8704. Min Range: -4.8704

Max Act: 4.8704. Min Act: -0.1700

Data Index: 7652125 (Open Web Text)

Max Activating Token Index: 160

Text #1

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.8355. Min Act: -0.1700

Data Index: 7163071 (Open Web Text)

Max Activating Token Index: 821

Text #2

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.8158. Min Act: -0.1700

Data Index: 584258 (Open Web Text)

Max Activating Token Index: 522

Text #3

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.8014. Min Act: -0.1700

Data Index: 5137620 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.8049. Min Act: -0.1700

Data Index: 1263694 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7827. Min Act: -0.1700

Data Index: 1843814 (Open Web Text)

Max Activating Token Index: 783

Text #6

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7506. Min Act: -0.1700

Data Index: 4163912 (Open Web Text)

Max Activating Token Index: 807

Text #7

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7854. Min Act: -0.1700

Data Index: 3319194 (Open Web Text)

Max Activating Token Index: 498

Text #8

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7854. Min Act: -0.1700

Data Index: 6269384 (Open Web Text)

Max Activating Token Index: 182

Text #9

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7811. Min Act: -0.1700

Data Index: 5694623 (Open Web Text)

Max Activating Token Index: 264

Text #10

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7236. Min Act: -0.1700

Data Index: 1177738 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7367. Min Act: -0.1700

Data Index: 8127803 (Open Web Text)

Max Activating Token Index: 708

Text #12

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7554. Min Act: -0.1700

Data Index: 2404465 (Open Web Text)

Max Activating Token Index: 857

Text #13

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7699. Min Act: -0.1700

Data Index: 6131521 (Open Web Text)

Max Activating Token Index: 259

Text #14

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7590. Min Act: -0.1700

Data Index: 4997034 (Open Web Text)

Max Activating Token Index: 833

Text #15

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7133. Min Act: -0.1700

Data Index: 3570412 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7450. Min Act: -0.1700

Data Index: 5782251 (Open Web Text)

Max Activating Token Index: 661

Text #17

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7291. Min Act: -0.1700

Data Index: 6935274 (Open Web Text)

Max Activating Token Index: 921

Text #18

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6925. Min Act: -0.1700

Data Index: 1327061 (Open Web Text)

Max Activating Token Index: 460

Text #19

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7476. Min Act: -0.1700

Data Index: 6458994 (Open Web Text)

Max Activating Token Index: 390