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

Dataset: Open Web Text

Neuron 2526 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: 5.9867. Min Range: -5.9867

Max Act: 5.9867. Min Act: -0.1700

Data Index: 4408716 (Open Web Text)

Max Activating Token Index: 382

Text #1

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.9286. Min Act: -0.1700

Data Index: 6820228 (Open Web Text)

Max Activating Token Index: 531

Text #2

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.5822. Min Act: -0.1700

Data Index: 4344147 (Open Web Text)

Max Activating Token Index: 595

Text #3

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.4364. Min Act: -0.1700

Data Index: 5179890 (Open Web Text)

Max Activating Token Index: 988

Text #4

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.3470. Min Act: -0.1700

Data Index: 1166652 (Open Web Text)

Max Activating Token Index: 874

Text #5

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.3184. Min Act: -0.1700

Data Index: 5092643 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.3591. Min Act: -0.1700

Data Index: 4170375 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.1668. Min Act: -0.1700

Data Index: 1576742 (Open Web Text)

Max Activating Token Index: 366

Text #8

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.2608. Min Act: -0.1700

Data Index: 4930666 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.2219. Min Act: -0.1700

Data Index: 3748826 (Open Web Text)

Max Activating Token Index: 138

Text #10

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.1878. Min Act: -0.1700

Data Index: 1720132 (Open Web Text)

Max Activating Token Index: 794

Text #11

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.2182. Min Act: -0.1700

Data Index: 663449 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.0610. Min Act: -0.1700

Data Index: 8594609 (Open Web Text)

Max Activating Token Index: 775

Text #13

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.0624. Min Act: -0.1700

Data Index: 7545383 (Open Web Text)

Max Activating Token Index: 406

Text #14

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.1327. Min Act: -0.1700

Data Index: 4098100 (Open Web Text)

Max Activating Token Index: 116

Text #15

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.0881. Min Act: -0.1700

Data Index: 1239954 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.1342. Min Act: -0.1700

Data Index: 5975986 (Open Web Text)

Max Activating Token Index: 329

Text #17

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.0968. Min Act: -0.1700

Data Index: 6503992 (Open Web Text)

Max Activating Token Index: 916

Text #18

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.0502. Min Act: -0.1700

Data Index: 6175736 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 5.9867. Min Range: -5.9867

Max Act: 5.0441. Min Act: -0.1700

Data Index: 5128322 (Open Web Text)

Max Activating Token Index: 36