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

Dataset: Open Web Text

Neuron 952 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: 4.0657. Min Range: -4.0657

Max Act: 4.0657. Min Act: -0.1700

Data Index: 7296810 (Open Web Text)

Max Activating Token Index: 131

Text #1

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.9531. Min Act: -0.1700

Data Index: 8691672 (Open Web Text)

Max Activating Token Index: 800

Text #2

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.9472. Min Act: -0.1700

Data Index: 8451547 (Open Web Text)

Max Activating Token Index: 909

Text #3

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.9219. Min Act: -0.1700

Data Index: 2511848 (Open Web Text)

Max Activating Token Index: 69

Text #4

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.9294. Min Act: -0.1700

Data Index: 480318 (Open Web Text)

Max Activating Token Index: 239

Text #5

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.9305. Min Act: -0.1700

Data Index: 6274889 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.9079. Min Act: -0.1700

Data Index: 6740099 (Open Web Text)

Max Activating Token Index: 994

Text #7

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.9371. Min Act: -0.1700

Data Index: 969817 (Open Web Text)

Max Activating Token Index: 528

Text #8

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.9176. Min Act: -0.1700

Data Index: 6555938 (Open Web Text)

Max Activating Token Index: 280

Text #9

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8814. Min Act: -0.1700

Data Index: 3200240 (Open Web Text)

Max Activating Token Index: 894

Text #10

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8926. Min Act: -0.1700

Data Index: 8346486 (Open Web Text)

Max Activating Token Index: 457

Text #11

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8814. Min Act: -0.1700

Data Index: 3938207 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8883. Min Act: -0.1700

Data Index: 7001486 (Open Web Text)

Max Activating Token Index: 286

Text #13

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8991. Min Act: -0.1700

Data Index: 1818038 (Open Web Text)

Max Activating Token Index: 150

Text #14

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8830. Min Act: -0.1700

Data Index: 3007067 (Open Web Text)

Max Activating Token Index: 729

Text #15

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8870. Min Act: -0.1700

Data Index: 2037481 (Open Web Text)

Max Activating Token Index: 509

Text #16

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8972. Min Act: -0.1700

Data Index: 6188915 (Open Web Text)

Max Activating Token Index: 334

Text #17

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8948. Min Act: -0.1700

Data Index: 2553942 (Open Web Text)

Max Activating Token Index: 187

Text #18

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8861. Min Act: -0.1700

Data Index: 4320227 (Open Web Text)

Max Activating Token Index: 407

Text #19

Max Range: 4.0657. Min Range: -4.0657

Max Act: 3.8975. Min Act: -0.1700

Data Index: 4056210 (Open Web Text)

Max Activating Token Index: 992