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

Dataset: Open Web Text

Neuron 2974 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: 2.9520. Min Range: -2.9520

Max Act: 2.9325. Min Act: -0.1700

Data Index: 1706806 (Open Web Text)

Max Activating Token Index: 562

Text #1

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9520. Min Act: -0.1700

Data Index: 1456921 (Open Web Text)

Max Activating Token Index: 403

Text #2

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9350. Min Act: -0.1700

Data Index: 2599782 (Open Web Text)

Max Activating Token Index: 848

Text #3

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9455. Min Act: -0.1700

Data Index: 8650007 (Open Web Text)

Max Activating Token Index: 388

Text #4

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9339. Min Act: -0.1700

Data Index: 7490432 (Open Web Text)

Max Activating Token Index: 238

Text #5

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9263. Min Act: -0.1700

Data Index: 8606936 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.8967. Min Act: -0.1700

Data Index: 2552405 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9047. Min Act: -0.1700

Data Index: 3903374 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9144. Min Act: -0.1700

Data Index: 1835515 (Open Web Text)

Max Activating Token Index: 127

Text #9

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9247. Min Act: -0.1700

Data Index: 8284928 (Open Web Text)

Max Activating Token Index: 956

Text #10

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9122. Min Act: -0.1700

Data Index: 5872239 (Open Web Text)

Max Activating Token Index: 861

Text #11

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.8940. Min Act: -0.1700

Data Index: 6794767 (Open Web Text)

Max Activating Token Index: 326

Text #12

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9113. Min Act: -0.1700

Data Index: 6528213 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9105. Min Act: -0.1700

Data Index: 3941631 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9007. Min Act: -0.1700

Data Index: 3671977 (Open Web Text)

Max Activating Token Index: 738

Text #15

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.8776. Min Act: -0.1700

Data Index: 4218427 (Open Web Text)

Max Activating Token Index: 176

Text #16

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.8883. Min Act: -0.1700

Data Index: 1845115 (Open Web Text)

Max Activating Token Index: 746

Text #17

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.8606. Min Act: -0.1700

Data Index: 8463799 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.8900. Min Act: -0.1700

Data Index: 1383108 (Open Web Text)

Max Activating Token Index: 86

Text #19

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.8836. Min Act: -0.1700

Data Index: 2209515 (Open Web Text)

Max Activating Token Index: 452