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

Dataset: Open Web Text

Neuron 1903 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: 5.3029. Min Range: -5.3029

Max Act: 5.3029. Min Act: -0.1700

Data Index: 227329 (Open Web Text)

Max Activating Token Index: 1013

Text #1

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.2218. Min Act: -0.1700

Data Index: 4532362 (Open Web Text)

Max Activating Token Index: 860

Text #2

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.1686. Min Act: -0.1700

Data Index: 1641853 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.1093. Min Act: -0.1700

Data Index: 5181386 (Open Web Text)

Max Activating Token Index: 490

Text #4

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.1227. Min Act: -0.1700

Data Index: 6961384 (Open Web Text)

Max Activating Token Index: 380

Text #5

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.1132. Min Act: -0.1700

Data Index: 5582261 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0946. Min Act: -0.1700

Data Index: 1386439 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0946. Min Act: -0.1700

Data Index: 1315341 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0817. Min Act: -0.1700

Data Index: 5751604 (Open Web Text)

Max Activating Token Index: 389

Text #9

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0826. Min Act: -0.1700

Data Index: 3504925 (Open Web Text)

Max Activating Token Index: 868

Text #10

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0797. Min Act: -0.1700

Data Index: 7680209 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0805. Min Act: -0.1700

Data Index: 3812861 (Open Web Text)

Max Activating Token Index: 232

Text #12

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0702. Min Act: -0.1700

Data Index: 7524539 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0591. Min Act: -0.1700

Data Index: 7205057 (Open Web Text)

Max Activating Token Index: 394

Text #14

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.1036. Min Act: -0.1700

Data Index: 2170861 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0946. Min Act: -0.1700

Data Index: 6301277 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0778. Min Act: -0.1700

Data Index: 6159814 (Open Web Text)

Max Activating Token Index: 831

Text #17

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0487. Min Act: -0.1700

Data Index: 4478502 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0487. Min Act: -0.1700

Data Index: 5809247 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 5.3029. Min Range: -5.3029

Max Act: 5.0560. Min Act: -0.1700

Data Index: 4728385 (Open Web Text)

Max Activating Token Index: 298