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

Dataset: Open Web Text

Neuron 37 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: 3.5084. Min Range: -3.5084

Max Act: 3.5084. Min Act: -0.1700

Data Index: 7759901 (Open Web Text)

Max Activating Token Index: 414

Text #1

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.4734. Min Act: -0.1700

Data Index: 5562513 (Open Web Text)

Max Activating Token Index: 178

Text #2

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.4771. Min Act: -0.1700

Data Index: 827035 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.4390. Min Act: -0.1700

Data Index: 827032 (Open Web Text)

Max Activating Token Index: 861

Text #4

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.4012. Min Act: -0.1700

Data Index: 827027 (Open Web Text)

Max Activating Token Index: 170

Text #5

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.3569. Min Act: -0.1700

Data Index: 7759895 (Open Web Text)

Max Activating Token Index: 782

Text #6

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.3637. Min Act: -0.1700

Data Index: 7759897 (Open Web Text)

Max Activating Token Index: 471

Text #7

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.3420. Min Act: -0.1700

Data Index: 827028 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.3410. Min Act: -0.1700

Data Index: 7759899 (Open Web Text)

Max Activating Token Index: 515

Text #9

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.3672. Min Act: -0.1700

Data Index: 827029 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.3406. Min Act: -0.1700

Data Index: 7759896 (Open Web Text)

Max Activating Token Index: 166

Text #11

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.3103. Min Act: -0.1700

Data Index: 4221520 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.3059. Min Act: -0.1700

Data Index: 7759898 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.2851. Min Act: -0.1700

Data Index: 2327168 (Open Web Text)

Max Activating Token Index: 172

Text #14

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.3061. Min Act: -0.1700

Data Index: 827033 (Open Web Text)

Max Activating Token Index: 642

Text #15

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.2775. Min Act: -0.1700

Data Index: 8653651 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.2614. Min Act: -0.1700

Data Index: 827030 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.2889. Min Act: -0.1700

Data Index: 2844611 (Open Web Text)

Max Activating Token Index: 265

Text #18

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.2745. Min Act: -0.1700

Data Index: 7669389 (Open Web Text)

Max Activating Token Index: 589

Text #19

Max Range: 3.5084. Min Range: -3.5084

Max Act: 3.2412. Min Act: -0.1700

Data Index: 827034 (Open Web Text)

Max Activating Token Index: 464