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

Dataset: Open Web Text

Neuron 1077 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: 3.5894. Min Range: -3.5894

Max Act: 3.5894. Min Act: -0.1700

Data Index: 5753225 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5307. Min Act: -0.1700

Data Index: 2551593 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5326. Min Act: -0.1700

Data Index: 3306788 (Open Web Text)

Max Activating Token Index: 56

Text #3

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5237. Min Act: -0.1700

Data Index: 4815958 (Open Web Text)

Max Activating Token Index: 772

Text #4

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5549. Min Act: -0.1700

Data Index: 1405816 (Open Web Text)

Max Activating Token Index: 177

Text #5

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5207. Min Act: -0.1700

Data Index: 4065887 (Open Web Text)

Max Activating Token Index: 492

Text #6

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4860. Min Act: -0.1700

Data Index: 1893629 (Open Web Text)

Max Activating Token Index: 166

Text #7

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4923. Min Act: -0.1700

Data Index: 3625201 (Open Web Text)

Max Activating Token Index: 258

Text #8

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4656. Min Act: -0.1700

Data Index: 1499337 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4825. Min Act: -0.1700

Data Index: 7960792 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4735. Min Act: -0.1700

Data Index: 2460386 (Open Web Text)

Max Activating Token Index: 937

Text #11

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4830. Min Act: -0.1700

Data Index: 928990 (Open Web Text)

Max Activating Token Index: 822

Text #12

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5087. Min Act: -0.1700

Data Index: 1626513 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4824. Min Act: -0.1700

Data Index: 7112563 (Open Web Text)

Max Activating Token Index: 435

Text #14

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4671. Min Act: -0.1700

Data Index: 8048476 (Open Web Text)

Max Activating Token Index: 760

Text #15

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4485. Min Act: -0.1700

Data Index: 6377180 (Open Web Text)

Max Activating Token Index: 758

Text #16

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4497. Min Act: -0.1700

Data Index: 7489237 (Open Web Text)

Max Activating Token Index: 965

Text #17

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4526. Min Act: -0.1700

Data Index: 2076850 (Open Web Text)

Max Activating Token Index: 200

Text #18

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4423. Min Act: -0.1700

Data Index: 3894044 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4618. Min Act: -0.1700

Data Index: 4197407 (Open Web Text)

Max Activating Token Index: 229