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

Dataset: Open Web Text

Neuron 536 in Layer 4

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: 3.8702. Min Range: -3.8702

Max Act: 3.8702. Min Act: -0.1700

Data Index: 5345795 (Open Web Text)

Max Activating Token Index: 811

Text #1

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.8525. Min Act: -0.1700

Data Index: 7426161 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.8193. Min Act: -0.1700

Data Index: 840233 (Open Web Text)

Max Activating Token Index: 167

Text #3

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.8130. Min Act: -0.1700

Data Index: 7592622 (Open Web Text)

Max Activating Token Index: 687

Text #4

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.8319. Min Act: -0.1700

Data Index: 5949890 (Open Web Text)

Max Activating Token Index: 824

Text #5

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.8227. Min Act: -0.1700

Data Index: 2669560 (Open Web Text)

Max Activating Token Index: 306

Text #6

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.8324. Min Act: -0.1700

Data Index: 175809 (Open Web Text)

Max Activating Token Index: 125

Text #7

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7960. Min Act: -0.1700

Data Index: 4364422 (Open Web Text)

Max Activating Token Index: 633

Text #8

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.8106. Min Act: -0.1700

Data Index: 7449960 (Open Web Text)

Max Activating Token Index: 834

Text #9

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7869. Min Act: -0.1700

Data Index: 2940564 (Open Web Text)

Max Activating Token Index: 56

Text #10

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.8025. Min Act: -0.1700

Data Index: 6447491 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.8189. Min Act: -0.1700

Data Index: 5457166 (Open Web Text)

Max Activating Token Index: 717

Text #12

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7684. Min Act: -0.1700

Data Index: 8822568 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7969. Min Act: -0.1700

Data Index: 1024589 (Open Web Text)

Max Activating Token Index: 971

Text #14

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7684. Min Act: -0.1700

Data Index: 4221445 (Open Web Text)

Max Activating Token Index: 97

Text #15

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7585. Min Act: -0.1700

Data Index: 8804323 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7416. Min Act: -0.1700

Data Index: 8713097 (Open Web Text)

Max Activating Token Index: 172

Text #17

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7452. Min Act: -0.1700

Data Index: 8349391 (Open Web Text)

Max Activating Token Index: 757

Text #18

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7436. Min Act: -0.1700

Data Index: 2943639 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7413. Min Act: -0.1700

Data Index: 2983130 (Open Web Text)

Max Activating Token Index: 90