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

Dataset: Open Web Text

Neuron 2560 in Layer 4

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: 3.7849. Min Range: -3.7849

Max Act: 3.7849. Min Act: -0.1700

Data Index: 314131 (Open Web Text)

Max Activating Token Index: 434

Text #1

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.7456. Min Act: -0.1700

Data Index: 1040654 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6999. Min Act: -0.1700

Data Index: 4195488 (Open Web Text)

Max Activating Token Index: 519

Text #3

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.7001. Min Act: -0.1700

Data Index: 3943741 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6837. Min Act: -0.1700

Data Index: 3769346 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.7115. Min Act: -0.1700

Data Index: 4522369 (Open Web Text)

Max Activating Token Index: 382

Text #6

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6784. Min Act: -0.1700

Data Index: 4217800 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6779. Min Act: -0.1700

Data Index: 6931682 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6513. Min Act: -0.1700

Data Index: 3544266 (Open Web Text)

Max Activating Token Index: 757

Text #9

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6581. Min Act: -0.1700

Data Index: 6915473 (Open Web Text)

Max Activating Token Index: 1002

Text #10

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6773. Min Act: -0.1700

Data Index: 5239651 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6794. Min Act: -0.1700

Data Index: 1354645 (Open Web Text)

Max Activating Token Index: 1011

Text #12

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6551. Min Act: -0.1700

Data Index: 3241234 (Open Web Text)

Max Activating Token Index: 994

Text #13

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6239. Min Act: -0.1700

Data Index: 7880927 (Open Web Text)

Max Activating Token Index: 135

Text #14

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.5932. Min Act: -0.1700

Data Index: 6578069 (Open Web Text)

Max Activating Token Index: 215

Text #15

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6138. Min Act: -0.1700

Data Index: 7661492 (Open Web Text)

Max Activating Token Index: 1005

Text #16

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6079. Min Act: -0.1700

Data Index: 7276207 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6728. Min Act: -0.1700

Data Index: 8475729 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.5950. Min Act: -0.1700

Data Index: 7743306 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 3.7849. Min Range: -3.7849

Max Act: 3.6182. Min Act: -0.1700

Data Index: 3423527 (Open Web Text)

Max Activating Token Index: 263