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

Dataset: Open Web Text

Neuron 1491 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: 4.0924. Min Range: -4.0924

Max Act: 4.0924. Min Act: -0.1700

Data Index: 3146636 (Open Web Text)

Max Activating Token Index: 68

Text #1

Max Range: 4.0924. Min Range: -4.0924

Max Act: 4.0234. Min Act: -0.1700

Data Index: 7278717 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9746. Min Act: -0.1700

Data Index: 6138352 (Open Web Text)

Max Activating Token Index: 208

Text #3

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9785. Min Act: -0.1700

Data Index: 7834387 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9695. Min Act: -0.1700

Data Index: 7178468 (Open Web Text)

Max Activating Token Index: 418

Text #5

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9687. Min Act: -0.1700

Data Index: 349517 (Open Web Text)

Max Activating Token Index: 107

Text #6

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9334. Min Act: -0.1700

Data Index: 3630659 (Open Web Text)

Max Activating Token Index: 285

Text #7

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9534. Min Act: -0.1700

Data Index: 7701827 (Open Web Text)

Max Activating Token Index: 957

Text #8

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9256. Min Act: -0.1700

Data Index: 3468774 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9109. Min Act: -0.1700

Data Index: 7751889 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9050. Min Act: -0.1700

Data Index: 4327210 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9311. Min Act: -0.1700

Data Index: 1497095 (Open Web Text)

Max Activating Token Index: 1002

Text #12

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.9080. Min Act: -0.1700

Data Index: 2500986 (Open Web Text)

Max Activating Token Index: 317

Text #13

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.8795. Min Act: -0.1700

Data Index: 7207103 (Open Web Text)

Max Activating Token Index: 496

Text #14

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.8822. Min Act: -0.1700

Data Index: 550242 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.8795. Min Act: -0.1700

Data Index: 1832499 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.8358. Min Act: -0.1700

Data Index: 1893997 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.8452. Min Act: -0.1700

Data Index: 5239517 (Open Web Text)

Max Activating Token Index: 87

Text #18

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.8542. Min Act: -0.1700

Data Index: 1464538 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 4.0924. Min Range: -4.0924

Max Act: 3.8756. Min Act: -0.1700

Data Index: 8363457 (Open Web Text)

Max Activating Token Index: 559