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

Dataset: Open Web Text

Neuron 2327 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: 3.2507. Min Range: -3.2507

Max Act: 3.2507. Min Act: -0.1700

Data Index: 8317684 (Open Web Text)

Max Activating Token Index: 944

Text #1

Max Range: 3.2507. Min Range: -3.2507

Max Act: 3.1857. Min Act: -0.1700

Data Index: 2559820 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 3.2507. Min Range: -3.2507

Max Act: 3.0843. Min Act: -0.1700

Data Index: 7066406 (Open Web Text)

Max Activating Token Index: 522

Text #3

Max Range: 3.2507. Min Range: -3.2507

Max Act: 3.0834. Min Act: -0.1700

Data Index: 1927104 (Open Web Text)

Max Activating Token Index: 979

Text #4

Max Range: 3.2507. Min Range: -3.2507

Max Act: 3.0500. Min Act: -0.1700

Data Index: 3760427 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 3.2507. Min Range: -3.2507

Max Act: 3.0561. Min Act: -0.1700

Data Index: 2559822 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 3.2507. Min Range: -3.2507

Max Act: 3.0296. Min Act: -0.1700

Data Index: 7094512 (Open Web Text)

Max Activating Token Index: 442

Text #7

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.9830. Min Act: -0.1700

Data Index: 6171960 (Open Web Text)

Max Activating Token Index: 833

Text #8

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.8943. Min Act: -0.1700

Data Index: 4515948 (Open Web Text)

Max Activating Token Index: 944

Text #9

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.9174. Min Act: -0.1700

Data Index: 736781 (Open Web Text)

Max Activating Token Index: 429

Text #10

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.9119. Min Act: -0.1700

Data Index: 5902155 (Open Web Text)

Max Activating Token Index: 353

Text #11

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.9287. Min Act: -0.1700

Data Index: 3711987 (Open Web Text)

Max Activating Token Index: 276

Text #12

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.9058. Min Act: -0.1700

Data Index: 6908136 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.9021. Min Act: -0.1700

Data Index: 5475734 (Open Web Text)

Max Activating Token Index: 979

Text #14

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.8917. Min Act: -0.1700

Data Index: 5189138 (Open Web Text)

Max Activating Token Index: 405

Text #15

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.8837. Min Act: -0.1700

Data Index: 5246155 (Open Web Text)

Max Activating Token Index: 641

Text #16

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.8613. Min Act: -0.1700

Data Index: 8210380 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.8361. Min Act: -0.1700

Data Index: 6434445 (Open Web Text)

Max Activating Token Index: 457

Text #18

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.8670. Min Act: -0.1700

Data Index: 300294 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 3.2507. Min Range: -3.2507

Max Act: 2.8428. Min Act: -0.1700

Data Index: 5271994 (Open Web Text)

Max Activating Token Index: 414