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

Dataset: Open Web Text

Neuron 1731 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: 3.2649. Min Range: -3.2649

Max Act: 3.2649. Min Act: -0.1700

Data Index: 825567 (Open Web Text)

Max Activating Token Index: 509

Text #1

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2604. Min Act: -0.1700

Data Index: 8358645 (Open Web Text)

Max Activating Token Index: 110

Text #2

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2609. Min Act: -0.1700

Data Index: 4666999 (Open Web Text)

Max Activating Token Index: 762

Text #3

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2472. Min Act: -0.1700

Data Index: 3894168 (Open Web Text)

Max Activating Token Index: 305

Text #4

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2213. Min Act: -0.1700

Data Index: 2548381 (Open Web Text)

Max Activating Token Index: 222

Text #5

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2124. Min Act: -0.1700

Data Index: 5401762 (Open Web Text)

Max Activating Token Index: 591

Text #6

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2101. Min Act: -0.1700

Data Index: 2275211 (Open Web Text)

Max Activating Token Index: 877

Text #7

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2148. Min Act: -0.1700

Data Index: 5673497 (Open Web Text)

Max Activating Token Index: 575

Text #8

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2282. Min Act: -0.1700

Data Index: 278267 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2195. Min Act: -0.1700

Data Index: 5509530 (Open Web Text)

Max Activating Token Index: 791

Text #10

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2002. Min Act: -0.1700

Data Index: 3110256 (Open Web Text)

Max Activating Token Index: 385

Text #11

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1832. Min Act: -0.1700

Data Index: 6468075 (Open Web Text)

Max Activating Token Index: 819

Text #12

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2029. Min Act: -0.1700

Data Index: 2297458 (Open Web Text)

Max Activating Token Index: 597

Text #13

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1898. Min Act: -0.1700

Data Index: 7687919 (Open Web Text)

Max Activating Token Index: 580

Text #14

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.2024. Min Act: -0.1700

Data Index: 5449243 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1952. Min Act: -0.1700

Data Index: 3495798 (Open Web Text)

Max Activating Token Index: 759

Text #16

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1928. Min Act: -0.1700

Data Index: 759669 (Open Web Text)

Max Activating Token Index: 341

Text #17

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1989. Min Act: -0.1700

Data Index: 8361623 (Open Web Text)

Max Activating Token Index: 398

Text #18

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1879. Min Act: -0.1700

Data Index: 1284649 (Open Web Text)

Max Activating Token Index: 575

Text #19

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1784. Min Act: -0.1700

Data Index: 8482832 (Open Web Text)

Max Activating Token Index: 778