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

Dataset: Open Web Text

Neuron 1942 in Layer 6

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: 5.3749. Min Range: -5.3749

Max Act: 5.3749. Min Act: -0.1700

Data Index: 4862269 (Open Web Text)

Max Activating Token Index: 192

Text #1

Max Range: 5.3749. Min Range: -5.3749

Max Act: 5.2642. Min Act: -0.1700

Data Index: 6069431 (Open Web Text)

Max Activating Token Index: 863

Text #2

Max Range: 5.3749. Min Range: -5.3749

Max Act: 5.1377. Min Act: -0.1700

Data Index: 3777671 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 5.3749. Min Range: -5.3749

Max Act: 5.1631. Min Act: -0.1700

Data Index: 4331981 (Open Web Text)

Max Activating Token Index: 775

Text #4

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9838. Min Act: -0.1700

Data Index: 3383041 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9937. Min Act: -0.1700

Data Index: 1146368 (Open Web Text)

Max Activating Token Index: 825

Text #6

Max Range: 5.3749. Min Range: -5.3749

Max Act: 5.0179. Min Act: -0.1700

Data Index: 5814723 (Open Web Text)

Max Activating Token Index: 102

Text #7

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9757. Min Act: -0.1700

Data Index: 899719 (Open Web Text)

Max Activating Token Index: 302

Text #8

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9489. Min Act: -0.1700

Data Index: 6533050 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9391. Min Act: -0.1700

Data Index: 4211306 (Open Web Text)

Max Activating Token Index: 984

Text #10

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9514. Min Act: -0.1700

Data Index: 2320100 (Open Web Text)

Max Activating Token Index: 546

Text #11

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9152. Min Act: -0.1700

Data Index: 5063755 (Open Web Text)

Max Activating Token Index: 735

Text #12

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9368. Min Act: -0.1700

Data Index: 6763935 (Open Web Text)

Max Activating Token Index: 713

Text #13

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9081. Min Act: -0.1700

Data Index: 2830351 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9382. Min Act: -0.1700

Data Index: 4970943 (Open Web Text)

Max Activating Token Index: 961

Text #15

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9298. Min Act: -0.1700

Data Index: 8270976 (Open Web Text)

Max Activating Token Index: 533

Text #16

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9258. Min Act: -0.1700

Data Index: 8464127 (Open Web Text)

Max Activating Token Index: 238

Text #17

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9248. Min Act: -0.1700

Data Index: 222483 (Open Web Text)

Max Activating Token Index: 742

Text #18

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.8906. Min Act: -0.1700

Data Index: 657566 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 5.3749. Min Range: -5.3749

Max Act: 4.9240. Min Act: -0.1700

Data Index: 5368785 (Open Web Text)

Max Activating Token Index: 509