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

Dataset: Open Web Text

Neuron 2104 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: 3.8569. Min Range: -3.8569

Max Act: 3.8569. Min Act: -0.1700

Data Index: 3857988 (Open Web Text)

Max Activating Token Index: 366

Text #1

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.8053. Min Act: -0.1700

Data Index: 4915607 (Open Web Text)

Max Activating Token Index: 298

Text #2

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.7179. Min Act: -0.1700

Data Index: 7755846 (Open Web Text)

Max Activating Token Index: 236

Text #3

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6865. Min Act: -0.1700

Data Index: 181011 (Open Web Text)

Max Activating Token Index: 735

Text #4

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6055. Min Act: -0.1700

Data Index: 1614578 (Open Web Text)

Max Activating Token Index: 395

Text #5

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6138. Min Act: -0.1700

Data Index: 1262170 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6144. Min Act: -0.1700

Data Index: 7779576 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6013. Min Act: -0.1700

Data Index: 107866 (Open Web Text)

Max Activating Token Index: 254

Text #8

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6124. Min Act: -0.1700

Data Index: 6392597 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5851. Min Act: -0.1700

Data Index: 5827668 (Open Web Text)

Max Activating Token Index: 399

Text #10

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5910. Min Act: -0.1700

Data Index: 7563845 (Open Web Text)

Max Activating Token Index: 80

Text #11

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5648. Min Act: -0.1700

Data Index: 1068074 (Open Web Text)

Max Activating Token Index: 889

Text #12

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5426. Min Act: -0.1700

Data Index: 7041287 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5339. Min Act: -0.1700

Data Index: 4019391 (Open Web Text)

Max Activating Token Index: 961

Text #14

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5575. Min Act: -0.1700

Data Index: 2211086 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5250. Min Act: -0.1700

Data Index: 7100939 (Open Web Text)

Max Activating Token Index: 757

Text #16

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5082. Min Act: -0.1700

Data Index: 1557526 (Open Web Text)

Max Activating Token Index: 617

Text #17

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5203. Min Act: -0.1700

Data Index: 2115980 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5137. Min Act: -0.1700

Data Index: 1364336 (Open Web Text)

Max Activating Token Index: 859

Text #19

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5240. Min Act: -0.1700

Data Index: 853713 (Open Web Text)

Max Activating Token Index: 907