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

Dataset: Open Web Text

Neuron 2267 in Layer 6

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: 5.3139. Min Range: -5.3139

Max Act: 5.3139. Min Act: -0.1700

Data Index: 831116 (Open Web Text)

Max Activating Token Index: 434

Text #1

Max Range: 5.3139. Min Range: -5.3139

Max Act: 5.1556. Min Act: -0.1700

Data Index: 2516009 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 5.3139. Min Range: -5.3139

Max Act: 5.1452. Min Act: -0.1700

Data Index: 251096 (Open Web Text)

Max Activating Token Index: 928

Text #3

Max Range: 5.3139. Min Range: -5.3139

Max Act: 5.0420. Min Act: -0.1700

Data Index: 6965670 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 5.3139. Min Range: -5.3139

Max Act: 5.0249. Min Act: -0.1700

Data Index: 3528939 (Open Web Text)

Max Activating Token Index: 74

Text #5

Max Range: 5.3139. Min Range: -5.3139

Max Act: 5.0019. Min Act: -0.1700

Data Index: 4582972 (Open Web Text)

Max Activating Token Index: 772

Text #6

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.9954. Min Act: -0.1700

Data Index: 6632909 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 5.3139. Min Range: -5.3139

Max Act: 5.0397. Min Act: -0.1700

Data Index: 3762031 (Open Web Text)

Max Activating Token Index: 554

Text #8

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.9295. Min Act: -0.1700

Data Index: 5797027 (Open Web Text)

Max Activating Token Index: 75

Text #9

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.9366. Min Act: -0.1700

Data Index: 2507285 (Open Web Text)

Max Activating Token Index: 244

Text #10

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.9424. Min Act: -0.1700

Data Index: 6660796 (Open Web Text)

Max Activating Token Index: 459

Text #11

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.8855. Min Act: -0.1700

Data Index: 5749419 (Open Web Text)

Max Activating Token Index: 671

Text #12

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.9187. Min Act: -0.1700

Data Index: 5179813 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.9174. Min Act: -0.1700

Data Index: 8603883 (Open Web Text)

Max Activating Token Index: 222

Text #14

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.9272. Min Act: -0.1700

Data Index: 4841345 (Open Web Text)

Max Activating Token Index: 444

Text #15

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.8642. Min Act: -0.1700

Data Index: 8456527 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.9038. Min Act: -0.1700

Data Index: 439108 (Open Web Text)

Max Activating Token Index: 920

Text #17

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.8838. Min Act: -0.1700

Data Index: 8062892 (Open Web Text)

Max Activating Token Index: 188

Text #18

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.8969. Min Act: -0.1700

Data Index: 7356987 (Open Web Text)

Max Activating Token Index: 757

Text #19

Max Range: 5.3139. Min Range: -5.3139

Max Act: 4.8778. Min Act: -0.1700

Data Index: 5951930 (Open Web Text)

Max Activating Token Index: 482