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

Dataset: Open Web Text

Neuron 855 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: 4.0723. Min Range: -4.0723

Max Act: 4.0723. Min Act: -0.1700

Data Index: 5521312 (Open Web Text)

Max Activating Token Index: 343

Text #1

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9696. Min Act: -0.1700

Data Index: 6759693 (Open Web Text)

Max Activating Token Index: 333

Text #2

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9624. Min Act: -0.1700

Data Index: 1461394 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9715. Min Act: -0.1700

Data Index: 3600471 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1074507 (Open Web Text)

Max Activating Token Index: 67

Text #5

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9334. Min Act: -0.1700

Data Index: 7036752 (Open Web Text)

Max Activating Token Index: 920

Text #6

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9410. Min Act: -0.1700

Data Index: 2393068 (Open Web Text)

Max Activating Token Index: 271

Text #7

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9291. Min Act: -0.1700

Data Index: 3967830 (Open Web Text)

Max Activating Token Index: 442

Text #8

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9119. Min Act: -0.1700

Data Index: 176646 (Open Web Text)

Max Activating Token Index: 138

Text #9

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9070. Min Act: -0.1700

Data Index: 1296827 (Open Web Text)

Max Activating Token Index: 273

Text #10

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.8951. Min Act: -0.1700

Data Index: 8571631 (Open Web Text)

Max Activating Token Index: 482

Text #11

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.9079. Min Act: -0.1700

Data Index: 4207089 (Open Web Text)

Max Activating Token Index: 319

Text #12

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.8513. Min Act: -0.1700

Data Index: 3687892 (Open Web Text)

Max Activating Token Index: 455

Text #13

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.8636. Min Act: -0.1700

Data Index: 6143012 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.8835. Min Act: -0.1700

Data Index: 8649447 (Open Web Text)

Max Activating Token Index: 898

Text #15

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.8609. Min Act: -0.1700

Data Index: 7548114 (Open Web Text)

Max Activating Token Index: 199

Text #16

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.8304. Min Act: -0.1700

Data Index: 171123 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.8590. Min Act: -0.1700

Data Index: 2801966 (Open Web Text)

Max Activating Token Index: 734

Text #18

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.8660. Min Act: -0.1700

Data Index: 5295273 (Open Web Text)

Max Activating Token Index: 640

Text #19

Max Range: 4.0723. Min Range: -4.0723

Max Act: 3.8578. Min Act: -0.1700

Data Index: 6646878 (Open Web Text)

Max Activating Token Index: 969