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

Dataset: Open Web Text

Neuron 2044 in Layer 5

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: 4.5272. Min Range: -4.5272

Max Act: 4.5272. Min Act: -0.1700

Data Index: 2856851 (Open Web Text)

Max Activating Token Index: 139

Text #1

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4738. Min Act: -0.1700

Data Index: 4841630 (Open Web Text)

Max Activating Token Index: 179

Text #2

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4856. Min Act: -0.1700

Data Index: 1866883 (Open Web Text)

Max Activating Token Index: 328

Text #3

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4406. Min Act: -0.1700

Data Index: 5352004 (Open Web Text)

Max Activating Token Index: 862

Text #4

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4751. Min Act: -0.1700

Data Index: 1880740 (Open Web Text)

Max Activating Token Index: 339

Text #5

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4735. Min Act: -0.1700

Data Index: 6277517 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4025. Min Act: -0.1700

Data Index: 8426529 (Open Web Text)

Max Activating Token Index: 156

Text #7

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4299. Min Act: -0.1700

Data Index: 7892746 (Open Web Text)

Max Activating Token Index: 338

Text #8

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4231. Min Act: -0.1700

Data Index: 3939088 (Open Web Text)

Max Activating Token Index: 1009

Text #9

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4002. Min Act: -0.1700

Data Index: 769647 (Open Web Text)

Max Activating Token Index: 535

Text #10

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4203. Min Act: -0.1700

Data Index: 4042166 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4235. Min Act: -0.1700

Data Index: 5721375 (Open Web Text)

Max Activating Token Index: 413

Text #12

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4083. Min Act: -0.1700

Data Index: 158934 (Open Web Text)

Max Activating Token Index: 863

Text #13

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.4059. Min Act: -0.1700

Data Index: 2661953 (Open Web Text)

Max Activating Token Index: 521

Text #14

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.3883. Min Act: -0.1700

Data Index: 3841095 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.3827. Min Act: -0.1700

Data Index: 3365543 (Open Web Text)

Max Activating Token Index: 605

Text #16

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.3830. Min Act: -0.1700

Data Index: 5704283 (Open Web Text)

Max Activating Token Index: 841

Text #17

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.3930. Min Act: -0.1700

Data Index: 5171038 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.3836. Min Act: -0.1700

Data Index: 3059386 (Open Web Text)

Max Activating Token Index: 903

Text #19

Max Range: 4.5272. Min Range: -4.5272

Max Act: 4.3799. Min Act: -0.1700

Data Index: 2991961 (Open Web Text)

Max Activating Token Index: 479