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

Dataset: Open Web Text

Neuron 1734 in Layer 3

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: 4.0591. Min Range: -4.0591

Max Act: 4.0591. Min Act: -0.1700

Data Index: 3394731 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.9862. Min Act: -0.1700

Data Index: 3791508 (Open Web Text)

Max Activating Token Index: 439

Text #2

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.9257. Min Act: -0.1700

Data Index: 2816451 (Open Web Text)

Max Activating Token Index: 728

Text #3

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8693. Min Act: -0.1700

Data Index: 8393205 (Open Web Text)

Max Activating Token Index: 382

Text #4

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8963. Min Act: -0.1700

Data Index: 7522784 (Open Web Text)

Max Activating Token Index: 350

Text #5

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8471. Min Act: -0.1700

Data Index: 8730907 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8633. Min Act: -0.1700

Data Index: 4147026 (Open Web Text)

Max Activating Token Index: 87

Text #7

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8878. Min Act: -0.1700

Data Index: 6851796 (Open Web Text)

Max Activating Token Index: 444

Text #8

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8721. Min Act: -0.1700

Data Index: 1493188 (Open Web Text)

Max Activating Token Index: 393

Text #9

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8679. Min Act: -0.1700

Data Index: 4911659 (Open Web Text)

Max Activating Token Index: 838

Text #10

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8277. Min Act: -0.1700

Data Index: 2812160 (Open Web Text)

Max Activating Token Index: 748

Text #11

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8287. Min Act: -0.1700

Data Index: 7330511 (Open Web Text)

Max Activating Token Index: 920

Text #12

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8079. Min Act: -0.1700

Data Index: 1251046 (Open Web Text)

Max Activating Token Index: 466

Text #13

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.7973. Min Act: -0.1700

Data Index: 4795162 (Open Web Text)

Max Activating Token Index: 576

Text #14

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8090. Min Act: -0.1700

Data Index: 1931407 (Open Web Text)

Max Activating Token Index: 730

Text #15

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8207. Min Act: -0.1700

Data Index: 3510185 (Open Web Text)

Max Activating Token Index: 705

Text #16

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8111. Min Act: -0.1700

Data Index: 1482387 (Open Web Text)

Max Activating Token Index: 469

Text #17

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.8024. Min Act: -0.1700

Data Index: 6027548 (Open Web Text)

Max Activating Token Index: 491

Text #18

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.7396. Min Act: -0.1700

Data Index: 7211709 (Open Web Text)

Max Activating Token Index: 876

Text #19

Max Range: 4.0591. Min Range: -4.0591

Max Act: 3.7780. Min Act: -0.1700

Data Index: 3816800 (Open Web Text)

Max Activating Token Index: 914