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

Dataset: Open Web Text

Neuron 2857 in Layer 3

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: 4.3923. Min Range: -4.3923

Max Act: 4.3923. Min Act: -0.1700

Data Index: 6129320 (Open Web Text)

Max Activating Token Index: 430

Text #1

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1993. Min Act: -0.1700

Data Index: 302165 (Open Web Text)

Max Activating Token Index: 182

Text #2

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1482. Min Act: -0.1700

Data Index: 3086418 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1198. Min Act: -0.1700

Data Index: 3395998 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.0100. Min Act: -0.1700

Data Index: 5434165 (Open Web Text)

Max Activating Token Index: 144

Text #5

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.0066. Min Act: -0.1700

Data Index: 482436 (Open Web Text)

Max Activating Token Index: 220

Text #6

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.0142. Min Act: -0.1700

Data Index: 7990103 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.0118. Min Act: -0.1700

Data Index: 2492146 (Open Web Text)

Max Activating Token Index: 735

Text #8

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.0242. Min Act: -0.1700

Data Index: 7931713 (Open Web Text)

Max Activating Token Index: 595

Text #9

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.0324. Min Act: -0.1700

Data Index: 8282419 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9729. Min Act: -0.1700

Data Index: 7802077 (Open Web Text)

Max Activating Token Index: 289

Text #11

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9687. Min Act: -0.1700

Data Index: 7043749 (Open Web Text)

Max Activating Token Index: 135

Text #12

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9721. Min Act: -0.1700

Data Index: 3950966 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9644. Min Act: -0.1700

Data Index: 8052544 (Open Web Text)

Max Activating Token Index: 113

Text #14

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9519. Min Act: -0.1700

Data Index: 141612 (Open Web Text)

Max Activating Token Index: 290

Text #15

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9538. Min Act: -0.1700

Data Index: 1750989 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9792. Min Act: -0.1700

Data Index: 6916433 (Open Web Text)

Max Activating Token Index: 317

Text #17

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9700. Min Act: -0.1700

Data Index: 6996340 (Open Web Text)

Max Activating Token Index: 299

Text #18

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9385. Min Act: -0.1700

Data Index: 1312859 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 4.3923. Min Range: -4.3923

Max Act: 3.9545. Min Act: -0.1700

Data Index: 3219294 (Open Web Text)

Max Activating Token Index: 1003