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

Dataset: Open Web Text

Neuron 2292 in Layer 6

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: 4.4072. Min Range: -4.4072

Max Act: 4.4072. Min Act: -0.1700

Data Index: 8602057 (Open Web Text)

Max Activating Token Index: 878

Text #1

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.3413. Min Act: -0.1700

Data Index: 5063959 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.2999. Min Act: -0.1700

Data Index: 7062911 (Open Web Text)

Max Activating Token Index: 276

Text #3

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.2970. Min Act: -0.1700

Data Index: 673626 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.2816. Min Act: -0.1700

Data Index: 8209198 (Open Web Text)

Max Activating Token Index: 1006

Text #5

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.2889. Min Act: -0.1700

Data Index: 5047849 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.2518. Min Act: -0.1700

Data Index: 1626473 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.2187. Min Act: -0.1700

Data Index: 6568293 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1820. Min Act: -0.1700

Data Index: 657592 (Open Web Text)

Max Activating Token Index: 616

Text #9

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1911. Min Act: -0.1700

Data Index: 3324857 (Open Web Text)

Max Activating Token Index: 639

Text #10

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.2020. Min Act: -0.1700

Data Index: 5808604 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1905. Min Act: -0.1700

Data Index: 2551467 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1689. Min Act: -0.1700

Data Index: 4105167 (Open Web Text)

Max Activating Token Index: 749

Text #13

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1517. Min Act: -0.1700

Data Index: 3500838 (Open Web Text)

Max Activating Token Index: 393

Text #14

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1746. Min Act: -0.1700

Data Index: 2743682 (Open Web Text)

Max Activating Token Index: 580

Text #15

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1595. Min Act: -0.1700

Data Index: 7459819 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1810. Min Act: -0.1700

Data Index: 4739966 (Open Web Text)

Max Activating Token Index: 599

Text #17

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1534. Min Act: -0.1700

Data Index: 6645211 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1227. Min Act: -0.1700

Data Index: 2877847 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 4.4072. Min Range: -4.4072

Max Act: 4.1178. Min Act: -0.1700

Data Index: 3327026 (Open Web Text)

Max Activating Token Index: 599