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

Dataset: Open Web Text

Neuron 752 in Layer 2

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: 4.9558. Min Range: -4.9558

Max Act: 4.9558. Min Act: -0.1700

Data Index: 8681639 (Open Web Text)

Max Activating Token Index: 663

Text #1

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.7979. Min Act: -0.1700

Data Index: 5996865 (Open Web Text)

Max Activating Token Index: 807

Text #2

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.7813. Min Act: -0.1700

Data Index: 6485003 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.7595. Min Act: -0.1700

Data Index: 954811 (Open Web Text)

Max Activating Token Index: 186

Text #4

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.7517. Min Act: -0.1700

Data Index: 5399910 (Open Web Text)

Max Activating Token Index: 508

Text #5

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.7181. Min Act: -0.1700

Data Index: 4710389 (Open Web Text)

Max Activating Token Index: 368

Text #6

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.7342. Min Act: -0.1700

Data Index: 6376544 (Open Web Text)

Max Activating Token Index: 838

Text #7

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.7287. Min Act: -0.1700

Data Index: 8089191 (Open Web Text)

Max Activating Token Index: 258

Text #8

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.7236. Min Act: -0.1700

Data Index: 4947331 (Open Web Text)

Max Activating Token Index: 577

Text #9

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6946. Min Act: -0.1700

Data Index: 1446522 (Open Web Text)

Max Activating Token Index: 868

Text #10

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6954. Min Act: -0.1700

Data Index: 8586213 (Open Web Text)

Max Activating Token Index: 994

Text #11

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6558. Min Act: -0.1700

Data Index: 3850787 (Open Web Text)

Max Activating Token Index: 76

Text #12

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6536. Min Act: -0.1700

Data Index: 3435574 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6676. Min Act: -0.1700

Data Index: 5527906 (Open Web Text)

Max Activating Token Index: 435

Text #14

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6952. Min Act: -0.1700

Data Index: 5996866 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6600. Min Act: -0.1700

Data Index: 6302062 (Open Web Text)

Max Activating Token Index: 723

Text #16

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6475. Min Act: -0.1700

Data Index: 6978689 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6290. Min Act: -0.1700

Data Index: 5610789 (Open Web Text)

Max Activating Token Index: 714

Text #18

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6297. Min Act: -0.1700

Data Index: 4669146 (Open Web Text)

Max Activating Token Index: 882

Text #19

Max Range: 4.9558. Min Range: -4.9558

Max Act: 4.6282. Min Act: -0.1700

Data Index: 1651554 (Open Web Text)

Max Activating Token Index: 929