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

Dataset: Open Web Text

Neuron 2729 in Layer 4

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: 3.1164. Min Range: -3.1164

Max Act: 3.1164. Min Act: -0.1700

Data Index: 4797024 (Open Web Text)

Max Activating Token Index: 285

Text #1

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0933. Min Act: -0.1700

Data Index: 7466099 (Open Web Text)

Max Activating Token Index: 900

Text #2

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0747. Min Act: -0.1700

Data Index: 1578931 (Open Web Text)

Max Activating Token Index: 168

Text #3

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0766. Min Act: -0.1700

Data Index: 1063465 (Open Web Text)

Max Activating Token Index: 587

Text #4

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0551. Min Act: -0.1700

Data Index: 1922686 (Open Web Text)

Max Activating Token Index: 366

Text #5

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0195. Min Act: -0.1700

Data Index: 5610127 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9908. Min Act: -0.1700

Data Index: 2968760 (Open Web Text)

Max Activating Token Index: 279

Text #7

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9544. Min Act: -0.1700

Data Index: 688167 (Open Web Text)

Max Activating Token Index: 599

Text #8

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9374. Min Act: -0.1700

Data Index: 6814000 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9078. Min Act: -0.1700

Data Index: 6196206 (Open Web Text)

Max Activating Token Index: 574

Text #10

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9358. Min Act: -0.1700

Data Index: 4499493 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9417. Min Act: -0.1700

Data Index: 5233833 (Open Web Text)

Max Activating Token Index: 213

Text #12

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9049. Min Act: -0.1700

Data Index: 4039170 (Open Web Text)

Max Activating Token Index: 531

Text #13

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9038. Min Act: -0.1700

Data Index: 4567405 (Open Web Text)

Max Activating Token Index: 392

Text #14

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9046. Min Act: -0.1700

Data Index: 1045056 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.8847. Min Act: -0.1700

Data Index: 1587597 (Open Web Text)

Max Activating Token Index: 834

Text #16

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.8960. Min Act: -0.1700

Data Index: 5915826 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9061. Min Act: -0.1700

Data Index: 7023996 (Open Web Text)

Max Activating Token Index: 1019

Text #18

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9008. Min Act: -0.1700

Data Index: 3994235 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.8961. Min Act: -0.1700

Data Index: 5772356 (Open Web Text)

Max Activating Token Index: 183