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

Dataset: Open Web Text

Neuron 2162 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: 4.9313. Min Range: -4.9313

Max Act: 4.9313. Min Act: -0.1700

Data Index: 5670480 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.8622. Min Act: -0.1700

Data Index: 7499067 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.8069. Min Act: -0.1700

Data Index: 1950866 (Open Web Text)

Max Activating Token Index: 298

Text #3

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7668. Min Act: -0.1700

Data Index: 391462 (Open Web Text)

Max Activating Token Index: 225

Text #4

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7711. Min Act: -0.1700

Data Index: 2640922 (Open Web Text)

Max Activating Token Index: 326

Text #5

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.8233. Min Act: -0.1700

Data Index: 1063746 (Open Web Text)

Max Activating Token Index: 986

Text #6

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7894. Min Act: -0.1700

Data Index: 8611503 (Open Web Text)

Max Activating Token Index: 166

Text #7

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7889. Min Act: -0.1700

Data Index: 4734373 (Open Web Text)

Max Activating Token Index: 69

Text #8

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7794. Min Act: -0.1700

Data Index: 6407654 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.7293. Min Act: -0.1700

Data Index: 2333673 (Open Web Text)

Max Activating Token Index: 858

Text #10

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.6889. Min Act: -0.1700

Data Index: 456431 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.6105. Min Act: -0.1700

Data Index: 2680133 (Open Web Text)

Max Activating Token Index: 106

Text #12

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.5583. Min Act: -0.1700

Data Index: 2247533 (Open Web Text)

Max Activating Token Index: 778

Text #13

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.5269. Min Act: -0.1700

Data Index: 4105997 (Open Web Text)

Max Activating Token Index: 355

Text #14

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.5133. Min Act: -0.1700

Data Index: 2377110 (Open Web Text)

Max Activating Token Index: 477

Text #15

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.4980. Min Act: -0.1700

Data Index: 3719232 (Open Web Text)

Max Activating Token Index: 238

Text #16

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.5201. Min Act: -0.1700

Data Index: 68440 (Open Web Text)

Max Activating Token Index: 106

Text #17

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.4967. Min Act: -0.1700

Data Index: 963184 (Open Web Text)

Max Activating Token Index: 981

Text #18

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.4846. Min Act: -0.1700

Data Index: 392113 (Open Web Text)

Max Activating Token Index: 726

Text #19

Max Range: 4.9313. Min Range: -4.9313

Max Act: 4.4925. Min Act: -0.1700

Data Index: 578512 (Open Web Text)

Max Activating Token Index: 238