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

Dataset: Open Web Text

Neuron 46 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: 6.1861. Min Range: -6.1861

Max Act: 6.1861. Min Act: -0.1700

Data Index: 754583 (Open Web Text)

Max Activating Token Index: 463

Text #1

Max Range: 6.1861. Min Range: -6.1861

Max Act: 6.0535. Min Act: -0.1700

Data Index: 2910820 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 6.1861. Min Range: -6.1861

Max Act: 6.0759. Min Act: -0.1697

Data Index: 6236779 (Open Web Text)

Max Activating Token Index: 504

Text #3

Max Range: 6.1861. Min Range: -6.1861

Max Act: 6.0520. Min Act: -0.1700

Data Index: 6086719 (Open Web Text)

Max Activating Token Index: 454

Text #4

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9749. Min Act: -0.1700

Data Index: 3427343 (Open Web Text)

Max Activating Token Index: 952

Text #5

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9914. Min Act: -0.1700

Data Index: 4074389 (Open Web Text)

Max Activating Token Index: 519

Text #6

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9346. Min Act: -0.1700

Data Index: 1558975 (Open Web Text)

Max Activating Token Index: 988

Text #7

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9665. Min Act: -0.1700

Data Index: 8143205 (Open Web Text)

Max Activating Token Index: 482

Text #8

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9567. Min Act: -0.1700

Data Index: 3245338 (Open Web Text)

Max Activating Token Index: 139

Text #9

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9714. Min Act: -0.1700

Data Index: 7980213 (Open Web Text)

Max Activating Token Index: 161

Text #10

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9980. Min Act: -0.1700

Data Index: 7419973 (Open Web Text)

Max Activating Token Index: 299

Text #11

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9185. Min Act: -0.1700

Data Index: 7999097 (Open Web Text)

Max Activating Token Index: 454

Text #12

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9600. Min Act: -0.1700

Data Index: 7747750 (Open Web Text)

Max Activating Token Index: 858

Text #13

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9358. Min Act: -0.1700

Data Index: 8341246 (Open Web Text)

Max Activating Token Index: 179

Text #14

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9167. Min Act: -0.1700

Data Index: 2892036 (Open Web Text)

Max Activating Token Index: 1001

Text #15

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.8920. Min Act: -0.1700

Data Index: 3743601 (Open Web Text)

Max Activating Token Index: 439

Text #16

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9582. Min Act: -0.1700

Data Index: 5475362 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9540. Min Act: -0.1700

Data Index: 2215607 (Open Web Text)

Max Activating Token Index: 357

Text #18

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.9539. Min Act: -0.1700

Data Index: 7156130 (Open Web Text)

Max Activating Token Index: 403

Text #19

Max Range: 6.1861. Min Range: -6.1861

Max Act: 5.8916. Min Act: -0.1700

Data Index: 1938389 (Open Web Text)

Max Activating Token Index: 656