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

Dataset: Open Web Text

Neuron 2059 in Layer 3

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: 2.7083. Min Range: -2.7083

Max Act: 2.7083. Min Act: -0.1700

Data Index: 7207938 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.6081. Min Act: -0.1700

Data Index: 4238124 (Open Web Text)

Max Activating Token Index: 572

Text #2

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.5982. Min Act: -0.1700

Data Index: 6797160 (Open Web Text)

Max Activating Token Index: 238

Text #3

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.5627. Min Act: -0.1700

Data Index: 8092050 (Open Web Text)

Max Activating Token Index: 890

Text #4

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.5334. Min Act: -0.1700

Data Index: 6750700 (Open Web Text)

Max Activating Token Index: 644

Text #5

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.5392. Min Act: -0.1700

Data Index: 3266329 (Open Web Text)

Max Activating Token Index: 215

Text #6

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.5071. Min Act: -0.1700

Data Index: 2449076 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.5454. Min Act: -0.1700

Data Index: 4628514 (Open Web Text)

Max Activating Token Index: 660

Text #8

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.5203. Min Act: -0.1700

Data Index: 5605675 (Open Web Text)

Max Activating Token Index: 530

Text #9

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4948. Min Act: -0.1700

Data Index: 6750701 (Open Web Text)

Max Activating Token Index: 601

Text #10

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4814. Min Act: -0.1700

Data Index: 7848754 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4771. Min Act: -0.1700

Data Index: 3392591 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4856. Min Act: -0.1700

Data Index: 1202824 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4933. Min Act: -0.1700

Data Index: 5435710 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4778. Min Act: -0.1700

Data Index: 668881 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4728. Min Act: -0.1700

Data Index: 1268072 (Open Web Text)

Max Activating Token Index: 442

Text #16

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4789. Min Act: -0.1700

Data Index: 7577778 (Open Web Text)

Max Activating Token Index: 235

Text #17

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4650. Min Act: -0.1700

Data Index: 6148234 (Open Web Text)

Max Activating Token Index: 342

Text #18

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4589. Min Act: -0.1700

Data Index: 6231901 (Open Web Text)

Max Activating Token Index: 364

Text #19

Max Range: 2.7083. Min Range: -2.7083

Max Act: 2.4847. Min Act: -0.1700

Data Index: 5275039 (Open Web Text)

Max Activating Token Index: 759