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

Dataset: Open Web Text

Neuron 462 in Layer 6

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: 5.1543. Min Range: -5.1543

Max Act: 5.1543. Min Act: -0.1700

Data Index: 3195505 (Open Web Text)

Max Activating Token Index: 154

Text #1

Max Range: 5.1543. Min Range: -5.1543

Max Act: 5.0866. Min Act: -0.1700

Data Index: 3755984 (Open Web Text)

Max Activating Token Index: 834

Text #2

Max Range: 5.1543. Min Range: -5.1543

Max Act: 5.0245. Min Act: -0.1700

Data Index: 5743342 (Open Web Text)

Max Activating Token Index: 804

Text #3

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.9387. Min Act: -0.1700

Data Index: 7150110 (Open Web Text)

Max Activating Token Index: 228

Text #4

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8973. Min Act: -0.1700

Data Index: 7120848 (Open Web Text)

Max Activating Token Index: 289

Text #5

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8594. Min Act: -0.1700

Data Index: 5191659 (Open Web Text)

Max Activating Token Index: 530

Text #6

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8615. Min Act: -0.1700

Data Index: 2153602 (Open Web Text)

Max Activating Token Index: 830

Text #7

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8725. Min Act: -0.1700

Data Index: 4861914 (Open Web Text)

Max Activating Token Index: 747

Text #8

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8683. Min Act: -0.1700

Data Index: 1305725 (Open Web Text)

Max Activating Token Index: 353

Text #9

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8907. Min Act: -0.1700

Data Index: 884748 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8212. Min Act: -0.1700

Data Index: 3309781 (Open Web Text)

Max Activating Token Index: 155

Text #11

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8144. Min Act: -0.1700

Data Index: 494795 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8101. Min Act: -0.1700

Data Index: 4408416 (Open Web Text)

Max Activating Token Index: 709

Text #13

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8081. Min Act: -0.1700

Data Index: 510481 (Open Web Text)

Max Activating Token Index: 899

Text #14

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8294. Min Act: -0.1700

Data Index: 2774587 (Open Web Text)

Max Activating Token Index: 232

Text #15

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8236. Min Act: -0.1700

Data Index: 5259072 (Open Web Text)

Max Activating Token Index: 814

Text #16

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.7914. Min Act: -0.1700

Data Index: 2074954 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8183. Min Act: -0.1700

Data Index: 6643648 (Open Web Text)

Max Activating Token Index: 798

Text #18

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.8089. Min Act: -0.1700

Data Index: 2777011 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 5.1543. Min Range: -5.1543

Max Act: 4.7696. Min Act: -0.1700

Data Index: 4234243 (Open Web Text)

Max Activating Token Index: 635