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

Dataset: Open Web Text

Neuron 232 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: 7.4827. Min Range: -7.4827

Max Act: 7.4827. Min Act: -0.1700

Data Index: 3617173 (Open Web Text)

Max Activating Token Index: 773

Text #1

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.4727. Min Act: -0.1700

Data Index: 4289078 (Open Web Text)

Max Activating Token Index: 200

Text #2

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.4785. Min Act: -0.1700

Data Index: 2559634 (Open Web Text)

Max Activating Token Index: 252

Text #3

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.3887. Min Act: -0.1700

Data Index: 1701079 (Open Web Text)

Max Activating Token Index: 184

Text #4

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.2835. Min Act: -0.1700

Data Index: 5318964 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.2863. Min Act: -0.1700

Data Index: 8090915 (Open Web Text)

Max Activating Token Index: 294

Text #6

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.2182. Min Act: -0.1700

Data Index: 6076860 (Open Web Text)

Max Activating Token Index: 954

Text #7

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.2372. Min Act: -0.1700

Data Index: 4805455 (Open Web Text)

Max Activating Token Index: 316

Text #8

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.2483. Min Act: -0.1700

Data Index: 3978211 (Open Web Text)

Max Activating Token Index: 653

Text #9

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.1878. Min Act: -0.1700

Data Index: 2013495 (Open Web Text)

Max Activating Token Index: 192

Text #10

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.1601. Min Act: -0.1700

Data Index: 1179125 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.0975. Min Act: -0.1700

Data Index: 2723939 (Open Web Text)

Max Activating Token Index: 107

Text #12

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.0840. Min Act: -0.1700

Data Index: 4289076 (Open Web Text)

Max Activating Token Index: 651

Text #13

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.0610. Min Act: -0.1700

Data Index: 4167728 (Open Web Text)

Max Activating Token Index: 287

Text #14

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.0513. Min Act: -0.1700

Data Index: 4248548 (Open Web Text)

Max Activating Token Index: 448

Text #15

Max Range: 7.4827. Min Range: -7.4827

Max Act: 7.0410. Min Act: -0.1700

Data Index: 3291892 (Open Web Text)

Max Activating Token Index: 353

Text #16

Max Range: 7.4827. Min Range: -7.4827

Max Act: 6.9437. Min Act: -0.1700

Data Index: 2693238 (Open Web Text)

Max Activating Token Index: 135

Text #17

Max Range: 7.4827. Min Range: -7.4827

Max Act: 6.8636. Min Act: -0.1700

Data Index: 2671576 (Open Web Text)

Max Activating Token Index: 783

Text #18

Max Range: 7.4827. Min Range: -7.4827

Max Act: 6.9205. Min Act: -0.1700

Data Index: 269187 (Open Web Text)

Max Activating Token Index: 737

Text #19

Max Range: 7.4827. Min Range: -7.4827

Max Act: 6.9406. Min Act: -0.1700

Data Index: 570619 (Open Web Text)

Max Activating Token Index: 429