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

Dataset: Open Web Text

Neuron 1922 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: 4.2480. Min Range: -4.2480

Max Act: 4.2285. Min Act: -0.1700

Data Index: 4110482 (Open Web Text)

Max Activating Token Index: 420

Text #1

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.2480. Min Act: -0.1700

Data Index: 3300325 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.2198. Min Act: -0.1700

Data Index: 4453442 (Open Web Text)

Max Activating Token Index: 683

Text #3

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.1824. Min Act: -0.1700

Data Index: 4968982 (Open Web Text)

Max Activating Token Index: 759

Text #4

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.1419. Min Act: -0.1700

Data Index: 3102760 (Open Web Text)

Max Activating Token Index: 1007

Text #5

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.1426. Min Act: -0.1700

Data Index: 1566991 (Open Web Text)

Max Activating Token Index: 310

Text #6

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.1713. Min Act: -0.1700

Data Index: 2287098 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.1124. Min Act: -0.1700

Data Index: 7245018 (Open Web Text)

Max Activating Token Index: 417

Text #8

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.0727. Min Act: -0.1700

Data Index: 5200829 (Open Web Text)

Max Activating Token Index: 993

Text #9

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.1011. Min Act: -0.1700

Data Index: 8601772 (Open Web Text)

Max Activating Token Index: 831

Text #10

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.0833. Min Act: -0.1700

Data Index: 6011593 (Open Web Text)

Max Activating Token Index: 989

Text #11

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.0816. Min Act: -0.1700

Data Index: 7245017 (Open Web Text)

Max Activating Token Index: 318

Text #12

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.1001. Min Act: -0.1700

Data Index: 2638970 (Open Web Text)

Max Activating Token Index: 488

Text #13

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.1009. Min Act: -0.1700

Data Index: 6946271 (Open Web Text)

Max Activating Token Index: 958

Text #14

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.0771. Min Act: -0.1700

Data Index: 1837610 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.0955. Min Act: -0.1700

Data Index: 8390214 (Open Web Text)

Max Activating Token Index: 594

Text #16

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.0184. Min Act: -0.1700

Data Index: 5807719 (Open Web Text)

Max Activating Token Index: 441

Text #17

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.0597. Min Act: -0.1700

Data Index: 1192095 (Open Web Text)

Max Activating Token Index: 933

Text #18

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.0534. Min Act: -0.1700

Data Index: 2975057 (Open Web Text)

Max Activating Token Index: 862

Text #19

Max Range: 4.2480. Min Range: -4.2480

Max Act: 4.0732. Min Act: -0.1700

Data Index: 6793202 (Open Web Text)

Max Activating Token Index: 400