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

Dataset: Open Web Text

Neuron 742 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: 4.1064. Min Range: -4.1064

Max Act: 4.1064. Min Act: -0.1700

Data Index: 2960097 (Open Web Text)

Max Activating Token Index: 662

Text #1

Max Range: 4.1064. Min Range: -4.1064

Max Act: 4.0973. Min Act: -0.1700

Data Index: 4921220 (Open Web Text)

Max Activating Token Index: 926

Text #2

Max Range: 4.1064. Min Range: -4.1064

Max Act: 4.0963. Min Act: -0.1700

Data Index: 8262086 (Open Web Text)

Max Activating Token Index: 608

Text #3

Max Range: 4.1064. Min Range: -4.1064

Max Act: 4.0571. Min Act: -0.1700

Data Index: 7407403 (Open Web Text)

Max Activating Token Index: 376

Text #4

Max Range: 4.1064. Min Range: -4.1064

Max Act: 4.0897. Min Act: -0.1700

Data Index: 5926722 (Open Web Text)

Max Activating Token Index: 544

Text #5

Max Range: 4.1064. Min Range: -4.1064

Max Act: 4.0251. Min Act: -0.1700

Data Index: 3154192 (Open Web Text)

Max Activating Token Index: 498

Text #6

Max Range: 4.1064. Min Range: -4.1064

Max Act: 4.0435. Min Act: -0.1700

Data Index: 1654859 (Open Web Text)

Max Activating Token Index: 291

Text #7

Max Range: 4.1064. Min Range: -4.1064

Max Act: 4.0347. Min Act: -0.1700

Data Index: 8560707 (Open Web Text)

Max Activating Token Index: 512

Text #8

Max Range: 4.1064. Min Range: -4.1064

Max Act: 4.0401. Min Act: -0.1700

Data Index: 7888599 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 4.1064. Min Range: -4.1064

Max Act: 4.0167. Min Act: -0.1700

Data Index: 85879 (Open Web Text)

Max Activating Token Index: 350

Text #10

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9941. Min Act: -0.1700

Data Index: 1485497 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9775. Min Act: -0.1700

Data Index: 4691126 (Open Web Text)

Max Activating Token Index: 949

Text #12

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9836. Min Act: -0.1700

Data Index: 4917864 (Open Web Text)

Max Activating Token Index: 743

Text #13

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9933. Min Act: -0.1700

Data Index: 6442858 (Open Web Text)

Max Activating Token Index: 175

Text #14

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9845. Min Act: -0.1700

Data Index: 6791094 (Open Web Text)

Max Activating Token Index: 401

Text #15

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9493. Min Act: -0.1700

Data Index: 4521334 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9587. Min Act: -0.1700

Data Index: 2361684 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9737. Min Act: -0.1700

Data Index: 3752108 (Open Web Text)

Max Activating Token Index: 792

Text #18

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9242. Min Act: -0.1700

Data Index: 529868 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 4.1064. Min Range: -4.1064

Max Act: 3.9328. Min Act: -0.1700

Data Index: 5496778 (Open Web Text)

Max Activating Token Index: 802