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

Dataset: Open Web Text

Neuron 253 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: 4.7136. Min Range: -4.7136

Max Act: 4.7136. Min Act: -0.1700

Data Index: 477865 (Open Web Text)

Max Activating Token Index: 723

Text #1

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.6511. Min Act: -0.1700

Data Index: 3993631 (Open Web Text)

Max Activating Token Index: 284

Text #2

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.6657. Min Act: -0.1700

Data Index: 8123782 (Open Web Text)

Max Activating Token Index: 854

Text #3

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.6033. Min Act: -0.1700

Data Index: 5864399 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.5640. Min Act: -0.1700

Data Index: 8825403 (Open Web Text)

Max Activating Token Index: 706

Text #5

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.5680. Min Act: -0.1700

Data Index: 2287059 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.5679. Min Act: -0.1700

Data Index: 7338853 (Open Web Text)

Max Activating Token Index: 960

Text #7

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.5549. Min Act: -0.1700

Data Index: 6917401 (Open Web Text)

Max Activating Token Index: 785

Text #8

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.5747. Min Act: -0.1700

Data Index: 1429504 (Open Web Text)

Max Activating Token Index: 525

Text #9

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.5103. Min Act: -0.1700

Data Index: 6692621 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.4896. Min Act: -0.1700

Data Index: 3514786 (Open Web Text)

Max Activating Token Index: 216

Text #11

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.4710. Min Act: -0.1700

Data Index: 1646797 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.4869. Min Act: -0.1700

Data Index: 6363212 (Open Web Text)

Max Activating Token Index: 205

Text #13

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.4527. Min Act: -0.1700

Data Index: 6044961 (Open Web Text)

Max Activating Token Index: 790

Text #14

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.4569. Min Act: -0.1700

Data Index: 2442645 (Open Web Text)

Max Activating Token Index: 494

Text #15

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.4430. Min Act: -0.1700

Data Index: 1911700 (Open Web Text)

Max Activating Token Index: 326

Text #16

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.4077. Min Act: -0.1700

Data Index: 3944609 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.4093. Min Act: -0.1700

Data Index: 5214414 (Open Web Text)

Max Activating Token Index: 925

Text #18

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.3966. Min Act: -0.1700

Data Index: 832169 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 4.7136. Min Range: -4.7136

Max Act: 4.4185. Min Act: -0.1700

Data Index: 866059 (Open Web Text)

Max Activating Token Index: 818