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

Dataset: Open Web Text

Neuron 2098 in Layer 0

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: 3.6277. Min Range: -3.6277

Max Act: 3.6277. Min Act: -0.1700

Data Index: 62403 (Open Web Text)

Max Activating Token Index: 680

Text #1

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.6150. Min Act: -0.1700

Data Index: 2465719 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5904. Min Act: -0.1700

Data Index: 3604125 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5904. Min Act: -0.1700

Data Index: 8683462 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5831. Min Act: -0.1700

Data Index: 2094754 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5665. Min Act: -0.1700

Data Index: 4332948 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5525. Min Act: -0.1700

Data Index: 1494731 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5749. Min Act: -0.1700

Data Index: 6465425 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5742. Min Act: -0.1700

Data Index: 8042316 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5420. Min Act: -0.1700

Data Index: 5393606 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5439. Min Act: -0.1700

Data Index: 4849444 (Open Web Text)

Max Activating Token Index: 635

Text #11

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5314. Min Act: -0.1700

Data Index: 636993 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5507. Min Act: -0.1700

Data Index: 3400853 (Open Web Text)

Max Activating Token Index: 727

Text #13

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5240. Min Act: -0.1700

Data Index: 1716592 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5320. Min Act: -0.1700

Data Index: 6171607 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5420. Min Act: -0.1700

Data Index: 950024 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5348. Min Act: -0.1700

Data Index: 2531505 (Open Web Text)

Max Activating Token Index: 665

Text #17

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5420. Min Act: -0.1700

Data Index: 4237410 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.5420. Min Act: -0.1700

Data Index: 4098602 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.6277. Min Range: -3.6277

Max Act: 3.4773. Min Act: -0.1700

Data Index: 3249963 (Open Web Text)

Max Activating Token Index: 807