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

Dataset: Open Web Text

Neuron 1102 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: 3.0245. Min Range: -3.0245

Max Act: 3.0245. Min Act: -0.1700

Data Index: 307211 (Open Web Text)

Max Activating Token Index: 588

Text #1

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9635. Min Act: -0.1700

Data Index: 2877860 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9596. Min Act: -0.1700

Data Index: 2204124 (Open Web Text)

Max Activating Token Index: 526

Text #3

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9843. Min Act: -0.1700

Data Index: 7096987 (Open Web Text)

Max Activating Token Index: 731

Text #4

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9701. Min Act: -0.1700

Data Index: 2706020 (Open Web Text)

Max Activating Token Index: 804

Text #5

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9590. Min Act: -0.1700

Data Index: 3540957 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9101. Min Act: -0.1700

Data Index: 5960718 (Open Web Text)

Max Activating Token Index: 851

Text #7

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9237. Min Act: -0.1700

Data Index: 6888138 (Open Web Text)

Max Activating Token Index: 87

Text #8

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9250. Min Act: -0.1700

Data Index: 6509334 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9147. Min Act: -0.1700

Data Index: 3586841 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9216. Min Act: -0.1700

Data Index: 4172152 (Open Web Text)

Max Activating Token Index: 651

Text #11

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9052. Min Act: -0.1700

Data Index: 2565124 (Open Web Text)

Max Activating Token Index: 897

Text #12

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9012. Min Act: -0.1700

Data Index: 8147446 (Open Web Text)

Max Activating Token Index: 399

Text #13

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9208. Min Act: -0.1700

Data Index: 5500281 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9102. Min Act: -0.1700

Data Index: 5731960 (Open Web Text)

Max Activating Token Index: 618

Text #15

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9110. Min Act: -0.1700

Data Index: 3063809 (Open Web Text)

Max Activating Token Index: 671

Text #16

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9050. Min Act: -0.1700

Data Index: 24015 (Open Web Text)

Max Activating Token Index: 942

Text #17

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8893. Min Act: -0.1700

Data Index: 5551234 (Open Web Text)

Max Activating Token Index: 858

Text #18

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.8918. Min Act: -0.1700

Data Index: 6130098 (Open Web Text)

Max Activating Token Index: 247

Text #19

Max Range: 3.0245. Min Range: -3.0245

Max Act: 2.9118. Min Act: -0.1700

Data Index: 5753463 (Open Web Text)

Max Activating Token Index: 939