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

Dataset: Open Web Text

Neuron 2694 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: 5.2766. Min Range: -5.2766

Max Act: 5.2766. Min Act: -0.1700

Data Index: 413161 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.2542. Min Act: -0.1700

Data Index: 1851504 (Open Web Text)

Max Activating Token Index: 134

Text #2

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.2398. Min Act: -0.1700

Data Index: 8321684 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.1654. Min Act: -0.1700

Data Index: 4098503 (Open Web Text)

Max Activating Token Index: 405

Text #4

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.1975. Min Act: -0.1700

Data Index: 934298 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.1856. Min Act: -0.1700

Data Index: 7256611 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.1736. Min Act: -0.1700

Data Index: 1090161 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.0975. Min Act: -0.1700

Data Index: 1333122 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.1423. Min Act: -0.1700

Data Index: 4031085 (Open Web Text)

Max Activating Token Index: 994

Text #9

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.2104. Min Act: -0.1700

Data Index: 2040262 (Open Web Text)

Max Activating Token Index: 321

Text #10

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.1078. Min Act: -0.1700

Data Index: 4056843 (Open Web Text)

Max Activating Token Index: 1016

Text #11

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.1327. Min Act: -0.1700

Data Index: 2132409 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.0642. Min Act: -0.1700

Data Index: 4925567 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.0879. Min Act: -0.1700

Data Index: 5019769 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.1432. Min Act: -0.1700

Data Index: 613134 (Open Web Text)

Max Activating Token Index: 751

Text #15

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.0641. Min Act: -0.1700

Data Index: 6269596 (Open Web Text)

Max Activating Token Index: 526

Text #16

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.0531. Min Act: -0.1700

Data Index: 3223280 (Open Web Text)

Max Activating Token Index: 200

Text #17

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.0501. Min Act: -0.1700

Data Index: 6962071 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.0260. Min Act: -0.1700

Data Index: 5658336 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 5.2766. Min Range: -5.2766

Max Act: 5.0882. Min Act: -0.1700

Data Index: 6001947 (Open Web Text)

Max Activating Token Index: 820