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

Dataset: Open Web Text

Neuron 1806 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: 5.3843. Min Range: -5.3843

Max Act: 5.3843. Min Act: -0.1700

Data Index: 6800892 (Open Web Text)

Max Activating Token Index: 311

Text #1

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.2190. Min Act: -0.1700

Data Index: 5241719 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.2107. Min Act: -0.1700

Data Index: 4706671 (Open Web Text)

Max Activating Token Index: 976

Text #3

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.1427. Min Act: -0.1700

Data Index: 140516 (Open Web Text)

Max Activating Token Index: 533

Text #4

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.1386. Min Act: -0.1700

Data Index: 7453438 (Open Web Text)

Max Activating Token Index: 517

Text #5

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0912. Min Act: -0.1700

Data Index: 7819237 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.1102. Min Act: -0.1700

Data Index: 1293059 (Open Web Text)

Max Activating Token Index: 847

Text #7

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0514. Min Act: -0.1700

Data Index: 2493242 (Open Web Text)

Max Activating Token Index: 393

Text #8

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0662. Min Act: -0.1700

Data Index: 7014745 (Open Web Text)

Max Activating Token Index: 314

Text #9

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0217. Min Act: -0.1700

Data Index: 7145128 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0045. Min Act: -0.1700

Data Index: 8722237 (Open Web Text)

Max Activating Token Index: 784

Text #11

Max Range: 5.3843. Min Range: -5.3843

Max Act: 4.9577. Min Act: -0.1700

Data Index: 5406069 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 5.3843. Min Range: -5.3843

Max Act: 4.9741. Min Act: -0.1700

Data Index: 753587 (Open Web Text)

Max Activating Token Index: 205

Text #13

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0361. Min Act: -0.1700

Data Index: 7955147 (Open Web Text)

Max Activating Token Index: 498

Text #14

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0220. Min Act: -0.1700

Data Index: 6990477 (Open Web Text)

Max Activating Token Index: 559

Text #15

Max Range: 5.3843. Min Range: -5.3843

Max Act: 4.9940. Min Act: -0.1700

Data Index: 8706774 (Open Web Text)

Max Activating Token Index: 769

Text #16

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0061. Min Act: -0.1700

Data Index: 1426244 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0512. Min Act: -0.1700

Data Index: 6103149 (Open Web Text)

Max Activating Token Index: 284

Text #18

Max Range: 5.3843. Min Range: -5.3843

Max Act: 4.9512. Min Act: -0.1699

Data Index: 5502863 (Open Web Text)

Max Activating Token Index: 780

Text #19

Max Range: 5.3843. Min Range: -5.3843

Max Act: 5.0129. Min Act: -0.1700

Data Index: 4638808 (Open Web Text)

Max Activating Token Index: 491