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

Dataset: Open Web Text

Neuron 2202 in Layer 2

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: 3.7117. Min Range: -3.7117

Max Act: 3.7117. Min Act: -0.1700

Data Index: 3679604 (Open Web Text)

Max Activating Token Index: 425

Text #1

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.6476. Min Act: -0.1700

Data Index: 6332087 (Open Web Text)

Max Activating Token Index: 969

Text #2

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.6098. Min Act: -0.1700

Data Index: 5953908 (Open Web Text)

Max Activating Token Index: 975

Text #3

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.6003. Min Act: -0.1700

Data Index: 7343668 (Open Web Text)

Max Activating Token Index: 889

Text #4

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5850. Min Act: -0.1700

Data Index: 3377378 (Open Web Text)

Max Activating Token Index: 998

Text #5

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5932. Min Act: -0.1700

Data Index: 5879658 (Open Web Text)

Max Activating Token Index: 298

Text #6

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5954. Min Act: -0.1700

Data Index: 2735008 (Open Web Text)

Max Activating Token Index: 117

Text #7

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5834. Min Act: -0.1700

Data Index: 1113361 (Open Web Text)

Max Activating Token Index: 154

Text #8

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5674. Min Act: -0.1700

Data Index: 2642025 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5780. Min Act: -0.1700

Data Index: 7148254 (Open Web Text)

Max Activating Token Index: 266

Text #10

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5730. Min Act: -0.1700

Data Index: 6332090 (Open Web Text)

Max Activating Token Index: 468

Text #11

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5941. Min Act: -0.1700

Data Index: 2004105 (Open Web Text)

Max Activating Token Index: 416

Text #12

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5352. Min Act: -0.1700

Data Index: 4822982 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5588. Min Act: -0.1700

Data Index: 2682267 (Open Web Text)

Max Activating Token Index: 929

Text #14

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5502. Min Act: -0.1700

Data Index: 4841507 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5487. Min Act: -0.1700

Data Index: 5206000 (Open Web Text)

Max Activating Token Index: 836

Text #16

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5505. Min Act: -0.1700

Data Index: 2907732 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5368. Min Act: -0.1700

Data Index: 5369176 (Open Web Text)

Max Activating Token Index: 185

Text #18

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5637. Min Act: -0.1700

Data Index: 378098 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.5389. Min Act: -0.1700

Data Index: 2990143 (Open Web Text)

Max Activating Token Index: 708