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

Dataset: Open Web Text

Neuron 1353 in Layer 3

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: 4.6872. Min Range: -4.6872

Max Act: 4.6872. Min Act: -0.1700

Data Index: 3055495 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6567. Min Act: -0.1700

Data Index: 4062960 (Open Web Text)

Max Activating Token Index: 426

Text #2

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6151. Min Act: -0.1700

Data Index: 6363693 (Open Web Text)

Max Activating Token Index: 761

Text #3

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6257. Min Act: -0.1700

Data Index: 5197230 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6161. Min Act: -0.1700

Data Index: 3318175 (Open Web Text)

Max Activating Token Index: 298

Text #5

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6259. Min Act: -0.1700

Data Index: 5898298 (Open Web Text)

Max Activating Token Index: 776

Text #6

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6358. Min Act: -0.1700

Data Index: 4396231 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5988. Min Act: -0.1700

Data Index: 2049873 (Open Web Text)

Max Activating Token Index: 683

Text #8

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6081. Min Act: -0.1700

Data Index: 1898809 (Open Web Text)

Max Activating Token Index: 907

Text #9

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6005. Min Act: -0.1700

Data Index: 6098832 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5960. Min Act: -0.1700

Data Index: 4423293 (Open Web Text)

Max Activating Token Index: 370

Text #11

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5911. Min Act: -0.1700

Data Index: 1025017 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5963. Min Act: -0.1700

Data Index: 1753532 (Open Web Text)

Max Activating Token Index: 505

Text #13

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5827. Min Act: -0.1700

Data Index: 8517054 (Open Web Text)

Max Activating Token Index: 812

Text #14

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6062. Min Act: -0.1700

Data Index: 8000762 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5852. Min Act: -0.1700

Data Index: 532151 (Open Web Text)

Max Activating Token Index: 583

Text #16

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5819. Min Act: -0.1700

Data Index: 6887871 (Open Web Text)

Max Activating Token Index: 700

Text #17

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5711. Min Act: -0.1700

Data Index: 3044446 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5519. Min Act: -0.1700

Data Index: 3287388 (Open Web Text)

Max Activating Token Index: 745

Text #19

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5534. Min Act: -0.1700

Data Index: 1842330 (Open Web Text)

Max Activating Token Index: 594