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

Dataset: Open Web Text

Neuron 975 in Layer 2

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: 3.8660. Min Range: -3.8660

Max Act: 3.8660. Min Act: -0.1700

Data Index: 6013726 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.8120. Min Act: -0.1700

Data Index: 1773137 (Open Web Text)

Max Activating Token Index: 442

Text #2

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7942. Min Act: -0.1700

Data Index: 6596085 (Open Web Text)

Max Activating Token Index: 930

Text #3

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7735. Min Act: -0.1700

Data Index: 8381653 (Open Web Text)

Max Activating Token Index: 247

Text #4

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7778. Min Act: -0.1700

Data Index: 7005780 (Open Web Text)

Max Activating Token Index: 123

Text #5

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7856. Min Act: -0.1700

Data Index: 6504407 (Open Web Text)

Max Activating Token Index: 263

Text #6

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7999. Min Act: -0.1700

Data Index: 2212174 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7382. Min Act: -0.1700

Data Index: 2597686 (Open Web Text)

Max Activating Token Index: 334

Text #8

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7115. Min Act: -0.1700

Data Index: 4300232 (Open Web Text)

Max Activating Token Index: 945

Text #9

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7388. Min Act: -0.1700

Data Index: 6956603 (Open Web Text)

Max Activating Token Index: 250

Text #10

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7504. Min Act: -0.1700

Data Index: 5481741 (Open Web Text)

Max Activating Token Index: 553

Text #11

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7403. Min Act: -0.1700

Data Index: 7307952 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7357. Min Act: -0.1700

Data Index: 7481465 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7371. Min Act: -0.1700

Data Index: 736431 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7141. Min Act: -0.1700

Data Index: 2985256 (Open Web Text)

Max Activating Token Index: 634

Text #15

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7280. Min Act: -0.1700

Data Index: 5157140 (Open Web Text)

Max Activating Token Index: 814

Text #16

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7351. Min Act: -0.1700

Data Index: 4110976 (Open Web Text)

Max Activating Token Index: 294

Text #17

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.6888. Min Act: -0.1700

Data Index: 8518695 (Open Web Text)

Max Activating Token Index: 186

Text #18

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.7014. Min Act: -0.1700

Data Index: 8066861 (Open Web Text)

Max Activating Token Index: 392

Text #19

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.6905. Min Act: -0.1700

Data Index: 5433077 (Open Web Text)

Max Activating Token Index: 568