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

Dataset: Open Web Text

Neuron 2420 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: 3.8394. Min Range: -3.8394

Max Act: 3.8394. Min Act: -0.1700

Data Index: 7088061 (Open Web Text)

Max Activating Token Index: 759

Text #1

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.7921. Min Act: -0.1700

Data Index: 5137354 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.7320. Min Act: -0.1700

Data Index: 8163841 (Open Web Text)

Max Activating Token Index: 339

Text #3

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.7191. Min Act: -0.1700

Data Index: 4401353 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.6483. Min Act: -0.1700

Data Index: 5347485 (Open Web Text)

Max Activating Token Index: 532

Text #5

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.6350. Min Act: -0.1700

Data Index: 6030185 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.6012. Min Act: -0.1700

Data Index: 2485321 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.5934. Min Act: -0.1700

Data Index: 8146973 (Open Web Text)

Max Activating Token Index: 836

Text #8

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.5782. Min Act: -0.1700

Data Index: 5208146 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.5732. Min Act: -0.1700

Data Index: 2452064 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.5115. Min Act: -0.1700

Data Index: 2539836 (Open Web Text)

Max Activating Token Index: 358

Text #11

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.5624. Min Act: -0.1700

Data Index: 4240660 (Open Web Text)

Max Activating Token Index: 780

Text #12

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.5137. Min Act: -0.1700

Data Index: 7797330 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.5507. Min Act: -0.1700

Data Index: 8255017 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.4772. Min Act: -0.1700

Data Index: 8260146 (Open Web Text)

Max Activating Token Index: 753

Text #15

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.5097. Min Act: -0.1700

Data Index: 5928369 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.5108. Min Act: -0.1700

Data Index: 1133121 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.4689. Min Act: -0.1700

Data Index: 6684380 (Open Web Text)

Max Activating Token Index: 226

Text #18

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.4980. Min Act: -0.1700

Data Index: 3880115 (Open Web Text)

Max Activating Token Index: 733

Text #19

Max Range: 3.8394. Min Range: -3.8394

Max Act: 3.4876. Min Act: -0.1700

Data Index: 2872268 (Open Web Text)

Max Activating Token Index: 830