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

Dataset: Open Web Text

Neuron 836 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: 3.8297. Min Range: -3.8297

Max Act: 3.8297. Min Act: -0.1700

Data Index: 4375108 (Open Web Text)

Max Activating Token Index: 899

Text #1

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.7607. Min Act: -0.1700

Data Index: 7302888 (Open Web Text)

Max Activating Token Index: 91

Text #2

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.7271. Min Act: -0.1700

Data Index: 6738723 (Open Web Text)

Max Activating Token Index: 36

Text #3

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.7370. Min Act: -0.1700

Data Index: 4121594 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.7322. Min Act: -0.1700

Data Index: 5726999 (Open Web Text)

Max Activating Token Index: 279

Text #5

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.7370. Min Act: -0.1700

Data Index: 4035271 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6955. Min Act: -0.1700

Data Index: 2918080 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6964. Min Act: -0.1700

Data Index: 1648216 (Open Web Text)

Max Activating Token Index: 984

Text #8

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6472. Min Act: -0.1700

Data Index: 2734215 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6683. Min Act: -0.1700

Data Index: 3765086 (Open Web Text)

Max Activating Token Index: 125

Text #10

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6762. Min Act: -0.1700

Data Index: 5137630 (Open Web Text)

Max Activating Token Index: 201

Text #11

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6548. Min Act: -0.1700

Data Index: 2950449 (Open Web Text)

Max Activating Token Index: 789

Text #12

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6346. Min Act: -0.1700

Data Index: 5382845 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6303. Min Act: -0.1700

Data Index: 3934370 (Open Web Text)

Max Activating Token Index: 1005

Text #14

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6087. Min Act: -0.1700

Data Index: 5261120 (Open Web Text)

Max Activating Token Index: 613

Text #15

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6550. Min Act: -0.1700

Data Index: 1273828 (Open Web Text)

Max Activating Token Index: 660

Text #16

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6001. Min Act: -0.1700

Data Index: 2558774 (Open Web Text)

Max Activating Token Index: 310

Text #17

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6025. Min Act: -0.1700

Data Index: 2592913 (Open Web Text)

Max Activating Token Index: 138

Text #18

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5948. Min Act: -0.1700

Data Index: 4063340 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5823. Min Act: -0.1700

Data Index: 4990031 (Open Web Text)

Max Activating Token Index: 88