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

Dataset: Open Web Text

Neuron 1666 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: 4.2232. Min Range: -4.2232

Max Act: 4.1913. Min Act: -0.1700

Data Index: 2431377 (Open Web Text)

Max Activating Token Index: 802

Text #1

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.2024. Min Act: -0.1700

Data Index: 3116282 (Open Web Text)

Max Activating Token Index: 896

Text #2

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.2232. Min Act: -0.1700

Data Index: 6785779 (Open Web Text)

Max Activating Token Index: 176

Text #3

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.2015. Min Act: -0.1700

Data Index: 7687002 (Open Web Text)

Max Activating Token Index: 127

Text #4

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.1545. Min Act: -0.1700

Data Index: 793768 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.1247. Min Act: -0.1700

Data Index: 5929720 (Open Web Text)

Max Activating Token Index: 804

Text #6

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.1025. Min Act: -0.1700

Data Index: 4455405 (Open Web Text)

Max Activating Token Index: 934

Text #7

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0977. Min Act: -0.1700

Data Index: 5687764 (Open Web Text)

Max Activating Token Index: 567

Text #8

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0916. Min Act: -0.1700

Data Index: 7777511 (Open Web Text)

Max Activating Token Index: 375

Text #9

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0911. Min Act: -0.1700

Data Index: 2434329 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0820. Min Act: -0.1700

Data Index: 2463069 (Open Web Text)

Max Activating Token Index: 285

Text #11

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.1030. Min Act: -0.1700

Data Index: 7394479 (Open Web Text)

Max Activating Token Index: 475

Text #12

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0517. Min Act: -0.1700

Data Index: 694847 (Open Web Text)

Max Activating Token Index: 708

Text #13

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0623. Min Act: -0.1700

Data Index: 2024480 (Open Web Text)

Max Activating Token Index: 836

Text #14

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0748. Min Act: -0.1700

Data Index: 2382288 (Open Web Text)

Max Activating Token Index: 290

Text #15

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0254. Min Act: -0.1700

Data Index: 7225362 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0228. Min Act: -0.1700

Data Index: 2093669 (Open Web Text)

Max Activating Token Index: 923

Text #17

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0175. Min Act: -0.1700

Data Index: 4160513 (Open Web Text)

Max Activating Token Index: 797

Text #18

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0423. Min Act: -0.1700

Data Index: 6775448 (Open Web Text)

Max Activating Token Index: 845

Text #19

Max Range: 4.2232. Min Range: -4.2232

Max Act: 4.0492. Min Act: -0.1700

Data Index: 6627553 (Open Web Text)

Max Activating Token Index: 523