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

Dataset: Open Web Text

Neuron 2105 in Layer 5

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: 3.8619. Min Range: -3.8619

Max Act: 3.8619. Min Act: -0.1700

Data Index: 3112065 (Open Web Text)

Max Activating Token Index: 550

Text #1

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.7511. Min Act: -0.1700

Data Index: 445969 (Open Web Text)

Max Activating Token Index: 252

Text #2

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.7862. Min Act: -0.1700

Data Index: 4628953 (Open Web Text)

Max Activating Token Index: 782

Text #3

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6351. Min Act: -0.1700

Data Index: 1647957 (Open Web Text)

Max Activating Token Index: 464

Text #4

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6218. Min Act: -0.1700

Data Index: 8231443 (Open Web Text)

Max Activating Token Index: 116

Text #5

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6217. Min Act: -0.1700

Data Index: 6481640 (Open Web Text)

Max Activating Token Index: 942

Text #6

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6475. Min Act: -0.1700

Data Index: 2628949 (Open Web Text)

Max Activating Token Index: 823

Text #7

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5898. Min Act: -0.1700

Data Index: 205895 (Open Web Text)

Max Activating Token Index: 738

Text #8

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6918. Min Act: -0.1700

Data Index: 7684722 (Open Web Text)

Max Activating Token Index: 536

Text #9

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6449. Min Act: -0.1700

Data Index: 5785511 (Open Web Text)

Max Activating Token Index: 317

Text #10

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6221. Min Act: -0.1700

Data Index: 6287731 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.6270. Min Act: -0.1700

Data Index: 1990865 (Open Web Text)

Max Activating Token Index: 602

Text #12

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5664. Min Act: -0.1700

Data Index: 5319153 (Open Web Text)

Max Activating Token Index: 272

Text #13

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5567. Min Act: -0.1700

Data Index: 2920901 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5337. Min Act: -0.1700

Data Index: 4827777 (Open Web Text)

Max Activating Token Index: 61

Text #15

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5199. Min Act: -0.1700

Data Index: 3362463 (Open Web Text)

Max Activating Token Index: 521

Text #16

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5071. Min Act: -0.1700

Data Index: 6340198 (Open Web Text)

Max Activating Token Index: 500

Text #17

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5055. Min Act: -0.1700

Data Index: 1841613 (Open Web Text)

Max Activating Token Index: 576

Text #18

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5179. Min Act: -0.1700

Data Index: 2658373 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 3.8619. Min Range: -3.8619

Max Act: 3.5484. Min Act: -0.1700

Data Index: 2308560 (Open Web Text)

Max Activating Token Index: 646