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

Dataset: Open Web Text

Neuron 2171 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: 4.6512. Min Range: -4.6512

Max Act: 4.6512. Min Act: -0.1700

Data Index: 1173585 (Open Web Text)

Max Activating Token Index: 974

Text #1

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.6110. Min Act: -0.1700

Data Index: 7721301 (Open Web Text)

Max Activating Token Index: 893

Text #2

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.6432. Min Act: -0.1700

Data Index: 3783796 (Open Web Text)

Max Activating Token Index: 353

Text #3

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.6058. Min Act: -0.1700

Data Index: 5710690 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5995. Min Act: -0.1700

Data Index: 5616503 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5919. Min Act: -0.1700

Data Index: 5251395 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5757. Min Act: -0.1700

Data Index: 5304514 (Open Web Text)

Max Activating Token Index: 38

Text #7

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5943. Min Act: -0.1700

Data Index: 2112633 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5829. Min Act: -0.1700

Data Index: 235916 (Open Web Text)

Max Activating Token Index: 334

Text #9

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5263. Min Act: -0.1700

Data Index: 4063745 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5598. Min Act: -0.1700

Data Index: 5990735 (Open Web Text)

Max Activating Token Index: 322

Text #11

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5625. Min Act: -0.1700

Data Index: 2922134 (Open Web Text)

Max Activating Token Index: 274

Text #12

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5758. Min Act: -0.1700

Data Index: 2101012 (Open Web Text)

Max Activating Token Index: 281

Text #13

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5764. Min Act: -0.1700

Data Index: 8144713 (Open Web Text)

Max Activating Token Index: 587

Text #14

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5500. Min Act: -0.1700

Data Index: 1281366 (Open Web Text)

Max Activating Token Index: 889

Text #15

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5605. Min Act: -0.1700

Data Index: 4144071 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5157. Min Act: -0.1700

Data Index: 2066407 (Open Web Text)

Max Activating Token Index: 163

Text #17

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5157. Min Act: -0.1700

Data Index: 921810 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5336. Min Act: -0.1700

Data Index: 6211965 (Open Web Text)

Max Activating Token Index: 398

Text #19

Max Range: 4.6512. Min Range: -4.6512

Max Act: 4.5115. Min Act: -0.1700

Data Index: 7040175 (Open Web Text)

Max Activating Token Index: 18