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

Dataset: Open Web Text

Neuron 2299 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: 3.3127. Min Range: -3.3127

Max Act: 3.3127. Min Act: -0.1700

Data Index: 6625141 (Open Web Text)

Max Activating Token Index: 122

Text #1

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.2652. Min Act: -0.1700

Data Index: 352306 (Open Web Text)

Max Activating Token Index: 444

Text #2

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.2424. Min Act: -0.1700

Data Index: 3431044 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.2421. Min Act: -0.1700

Data Index: 1102666 (Open Web Text)

Max Activating Token Index: 90

Text #4

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.2149. Min Act: -0.1700

Data Index: 4341007 (Open Web Text)

Max Activating Token Index: 440

Text #5

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.2260. Min Act: -0.1700

Data Index: 8221078 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.2018. Min Act: -0.1700

Data Index: 7163783 (Open Web Text)

Max Activating Token Index: 865

Text #7

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.2147. Min Act: -0.1700

Data Index: 2240968 (Open Web Text)

Max Activating Token Index: 420

Text #8

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1873. Min Act: -0.1700

Data Index: 2440624 (Open Web Text)

Max Activating Token Index: 147

Text #9

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1906. Min Act: -0.1700

Data Index: 8261580 (Open Web Text)

Max Activating Token Index: 457

Text #10

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1923. Min Act: -0.1700

Data Index: 7503175 (Open Web Text)

Max Activating Token Index: 580

Text #11

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1508. Min Act: -0.1700

Data Index: 697206 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1525. Min Act: -0.1700

Data Index: 6886985 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1638. Min Act: -0.1700

Data Index: 2800681 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1818. Min Act: -0.1700

Data Index: 2262883 (Open Web Text)

Max Activating Token Index: 390

Text #15

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1628. Min Act: -0.1700

Data Index: 6106018 (Open Web Text)

Max Activating Token Index: 148

Text #16

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1632. Min Act: -0.1700

Data Index: 3933400 (Open Web Text)

Max Activating Token Index: 576

Text #17

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1674. Min Act: -0.1700

Data Index: 3946088 (Open Web Text)

Max Activating Token Index: 706

Text #18

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1374. Min Act: -0.1700

Data Index: 329093 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.1439. Min Act: -0.1700

Data Index: 188699 (Open Web Text)

Max Activating Token Index: 142