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

Dataset: Open Web Text

Neuron 448 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: 4.4602. Min Range: -4.4602

Max Act: 4.4602. Min Act: -0.1700

Data Index: 3707040 (Open Web Text)

Max Activating Token Index: 504

Text #1

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.4060. Min Act: -0.1700

Data Index: 3446532 (Open Web Text)

Max Activating Token Index: 457

Text #2

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.2916. Min Act: -0.1700

Data Index: 4410132 (Open Web Text)

Max Activating Token Index: 508

Text #3

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.2569. Min Act: -0.1700

Data Index: 3093191 (Open Web Text)

Max Activating Token Index: 835

Text #4

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.2594. Min Act: -0.1700

Data Index: 7517918 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.2839. Min Act: -0.1700

Data Index: 7107067 (Open Web Text)

Max Activating Token Index: 770

Text #6

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.2492. Min Act: -0.1700

Data Index: 3575819 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.2342. Min Act: -0.1700

Data Index: 1201093 (Open Web Text)

Max Activating Token Index: 960

Text #8

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.2051. Min Act: -0.1700

Data Index: 7971818 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.1564. Min Act: -0.1700

Data Index: 307487 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.1589. Min Act: -0.1700

Data Index: 156944 (Open Web Text)

Max Activating Token Index: 242

Text #11

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.1629. Min Act: -0.1700

Data Index: 3303799 (Open Web Text)

Max Activating Token Index: 667

Text #12

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.1301. Min Act: -0.1700

Data Index: 3412861 (Open Web Text)

Max Activating Token Index: 660

Text #13

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.1353. Min Act: -0.1700

Data Index: 689996 (Open Web Text)

Max Activating Token Index: 884

Text #14

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.1674. Min Act: -0.1700

Data Index: 1246592 (Open Web Text)

Max Activating Token Index: 801

Text #15

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.1374. Min Act: -0.1700

Data Index: 3048586 (Open Web Text)

Max Activating Token Index: 992

Text #16

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.1127. Min Act: -0.1700

Data Index: 2132709 (Open Web Text)

Max Activating Token Index: 712

Text #17

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.0541. Min Act: -0.1700

Data Index: 3132247 (Open Web Text)

Max Activating Token Index: 245

Text #18

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.0965. Min Act: -0.1700

Data Index: 2709105 (Open Web Text)

Max Activating Token Index: 505

Text #19

Max Range: 4.4602. Min Range: -4.4602

Max Act: 4.1114. Min Act: -0.1700

Data Index: 7155611 (Open Web Text)

Max Activating Token Index: 399