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

Dataset: Open Web Text

Neuron 1368 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: 3.8136. Min Range: -3.8136

Max Act: 3.8136. Min Act: -0.1700

Data Index: 5787065 (Open Web Text)

Max Activating Token Index: 610

Text #1

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.7711. Min Act: -0.1700

Data Index: 3811398 (Open Web Text)

Max Activating Token Index: 379

Text #2

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.7170. Min Act: -0.1700

Data Index: 4581382 (Open Web Text)

Max Activating Token Index: 800

Text #3

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6865. Min Act: -0.1700

Data Index: 6829892 (Open Web Text)

Max Activating Token Index: 925

Text #4

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6618. Min Act: -0.1700

Data Index: 8712544 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6545. Min Act: -0.1700

Data Index: 2467034 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6672. Min Act: -0.1700

Data Index: 6739062 (Open Web Text)

Max Activating Token Index: 592

Text #7

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6269. Min Act: -0.1700

Data Index: 3675754 (Open Web Text)

Max Activating Token Index: 220

Text #8

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6277. Min Act: -0.1700

Data Index: 1849160 (Open Web Text)

Max Activating Token Index: 825

Text #9

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6301. Min Act: -0.1700

Data Index: 3729710 (Open Web Text)

Max Activating Token Index: 98

Text #10

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6245. Min Act: -0.1700

Data Index: 685326 (Open Web Text)

Max Activating Token Index: 672

Text #11

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6085. Min Act: -0.1700

Data Index: 6771424 (Open Web Text)

Max Activating Token Index: 257

Text #12

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6162. Min Act: -0.1700

Data Index: 5704643 (Open Web Text)

Max Activating Token Index: 587

Text #13

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6245. Min Act: -0.1700

Data Index: 4387459 (Open Web Text)

Max Activating Token Index: 787

Text #14

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.5912. Min Act: -0.1700

Data Index: 5606539 (Open Web Text)

Max Activating Token Index: 392

Text #15

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6034. Min Act: -0.1700

Data Index: 4581381 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.5845. Min Act: -0.1700

Data Index: 7705417 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.5852. Min Act: -0.1700

Data Index: 7990584 (Open Web Text)

Max Activating Token Index: 682

Text #18

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.6004. Min Act: -0.1700

Data Index: 591315 (Open Web Text)

Max Activating Token Index: 327

Text #19

Max Range: 3.8136. Min Range: -3.8136

Max Act: 3.5682. Min Act: -0.1700

Data Index: 6693959 (Open Web Text)

Max Activating Token Index: 193