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

Dataset: Open Web Text

Neuron 739 in Layer 6

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: 6.1497. Min Range: -6.1497

Max Act: 6.1497. Min Act: -0.1700

Data Index: 5096526 (Open Web Text)

Max Activating Token Index: 748

Text #1

Max Range: 6.1497. Min Range: -6.1497

Max Act: 6.1203. Min Act: -0.1700

Data Index: 8109501 (Open Web Text)

Max Activating Token Index: 630

Text #2

Max Range: 6.1497. Min Range: -6.1497

Max Act: 6.0988. Min Act: -0.1700

Data Index: 2111148 (Open Web Text)

Max Activating Token Index: 198

Text #3

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.9932. Min Act: -0.1700

Data Index: 1018914 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 6.1497. Min Range: -6.1497

Max Act: 6.0118. Min Act: -0.1700

Data Index: 6066457 (Open Web Text)

Max Activating Token Index: 977

Text #5

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.8863. Min Act: -0.1700

Data Index: 8570752 (Open Web Text)

Max Activating Token Index: 87

Text #6

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.8974. Min Act: -0.1700

Data Index: 8732961 (Open Web Text)

Max Activating Token Index: 781

Text #7

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.7823. Min Act: -0.1700

Data Index: 5534831 (Open Web Text)

Max Activating Token Index: 515

Text #8

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.8387. Min Act: -0.1700

Data Index: 1294754 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.8656. Min Act: -0.1700

Data Index: 4624360 (Open Web Text)

Max Activating Token Index: 302

Text #10

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.8107. Min Act: -0.1700

Data Index: 4498176 (Open Web Text)

Max Activating Token Index: 644

Text #11

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.8000. Min Act: -0.1700

Data Index: 624934 (Open Web Text)

Max Activating Token Index: 764

Text #12

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.7255. Min Act: -0.1700

Data Index: 6657756 (Open Web Text)

Max Activating Token Index: 366

Text #13

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.7426. Min Act: -0.1700

Data Index: 7655794 (Open Web Text)

Max Activating Token Index: 768

Text #14

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.7457. Min Act: -0.1700

Data Index: 1281006 (Open Web Text)

Max Activating Token Index: 730

Text #15

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.7611. Min Act: -0.1700

Data Index: 6576347 (Open Web Text)

Max Activating Token Index: 490

Text #16

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.7684. Min Act: -0.1700

Data Index: 4384494 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.7183. Min Act: -0.1700

Data Index: 4895480 (Open Web Text)

Max Activating Token Index: 609

Text #18

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.7565. Min Act: -0.1700

Data Index: 5550219 (Open Web Text)

Max Activating Token Index: 920

Text #19

Max Range: 6.1497. Min Range: -6.1497

Max Act: 5.7365. Min Act: -0.1700

Data Index: 5521421 (Open Web Text)

Max Activating Token Index: 52