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

Dataset: Open Web Text

Neuron 2954 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: 4.7781. Min Range: -4.7781

Max Act: 4.7781. Min Act: -0.1700

Data Index: 3726326 (Open Web Text)

Max Activating Token Index: 291

Text #1

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.6228. Min Act: -0.1700

Data Index: 8032606 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4872. Min Act: -0.1700

Data Index: 1561292 (Open Web Text)

Max Activating Token Index: 121

Text #3

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4655. Min Act: -0.1700

Data Index: 1923546 (Open Web Text)

Max Activating Token Index: 503

Text #4

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4723. Min Act: -0.1700

Data Index: 6625888 (Open Web Text)

Max Activating Token Index: 220

Text #5

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.5508. Min Act: -0.1700

Data Index: 6477435 (Open Web Text)

Max Activating Token Index: 261

Text #6

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.5422. Min Act: -0.1700

Data Index: 5892032 (Open Web Text)

Max Activating Token Index: 462

Text #7

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4871. Min Act: -0.1700

Data Index: 8548521 (Open Web Text)

Max Activating Token Index: 361

Text #8

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4464. Min Act: -0.1700

Data Index: 8645343 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.5039. Min Act: -0.1700

Data Index: 4970241 (Open Web Text)

Max Activating Token Index: 175

Text #10

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4671. Min Act: -0.1700

Data Index: 355050 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4634. Min Act: -0.1700

Data Index: 1645368 (Open Web Text)

Max Activating Token Index: 703

Text #12

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4339. Min Act: -0.1700

Data Index: 1732207 (Open Web Text)

Max Activating Token Index: 794

Text #13

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4291. Min Act: -0.1700

Data Index: 6915166 (Open Web Text)

Max Activating Token Index: 396

Text #14

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4109. Min Act: -0.1700

Data Index: 6672574 (Open Web Text)

Max Activating Token Index: 331

Text #15

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.3908. Min Act: -0.1700

Data Index: 7791874 (Open Web Text)

Max Activating Token Index: 735

Text #16

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.4486. Min Act: -0.1700

Data Index: 2202924 (Open Web Text)

Max Activating Token Index: 71

Text #17

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.3895. Min Act: -0.1700

Data Index: 1011614 (Open Web Text)

Max Activating Token Index: 43

Text #18

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.3381. Min Act: -0.1700

Data Index: 1833198 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 4.7781. Min Range: -4.7781

Max Act: 4.3301. Min Act: -0.1700

Data Index: 4194145 (Open Web Text)

Max Activating Token Index: 807