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

Dataset: Open Web Text

Neuron 2085 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: 4.7921. Min Range: -4.7921

Max Act: 4.7921. Min Act: -0.1700

Data Index: 6946817 (Open Web Text)

Max Activating Token Index: 140

Text #1

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.5971. Min Act: -0.1700

Data Index: 7882516 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.5738. Min Act: -0.1700

Data Index: 3549539 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.5294. Min Act: -0.1700

Data Index: 4247260 (Open Web Text)

Max Activating Token Index: 485

Text #4

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.5350. Min Act: -0.1700

Data Index: 8483069 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.5298. Min Act: -0.1700

Data Index: 845740 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.5370. Min Act: -0.1700

Data Index: 5723990 (Open Web Text)

Max Activating Token Index: 339

Text #7

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.5253. Min Act: -0.1700

Data Index: 722652 (Open Web Text)

Max Activating Token Index: 789

Text #8

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.5418. Min Act: -0.1700

Data Index: 8689916 (Open Web Text)

Max Activating Token Index: 754

Text #9

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4990. Min Act: -0.1700

Data Index: 7563761 (Open Web Text)

Max Activating Token Index: 735

Text #10

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.5030. Min Act: -0.1700

Data Index: 1279279 (Open Web Text)

Max Activating Token Index: 251

Text #11

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4657. Min Act: -0.1700

Data Index: 2491357 (Open Web Text)

Max Activating Token Index: 996

Text #12

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4725. Min Act: -0.1700

Data Index: 2332546 (Open Web Text)

Max Activating Token Index: 355

Text #13

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4901. Min Act: -0.1700

Data Index: 1490662 (Open Web Text)

Max Activating Token Index: 871

Text #14

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4785. Min Act: -0.1700

Data Index: 1786009 (Open Web Text)

Max Activating Token Index: 130

Text #15

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4526. Min Act: -0.1700

Data Index: 3582997 (Open Web Text)

Max Activating Token Index: 640

Text #16

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4610. Min Act: -0.1700

Data Index: 2708190 (Open Web Text)

Max Activating Token Index: 79

Text #17

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4686. Min Act: -0.1700

Data Index: 429546 (Open Web Text)

Max Activating Token Index: 930

Text #18

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4217. Min Act: -0.1700

Data Index: 2889336 (Open Web Text)

Max Activating Token Index: 531

Text #19

Max Range: 4.7921. Min Range: -4.7921

Max Act: 4.4430. Min Act: -0.1700

Data Index: 3023482 (Open Web Text)

Max Activating Token Index: 846