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

Dataset: Open Web Text

Neuron 669 in Layer 2

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: 5.3658. Min Range: -5.3658

Max Act: 5.3658. Min Act: -0.1700

Data Index: 4358475 (Open Web Text)

Max Activating Token Index: 987

Text #1

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.3354. Min Act: -0.1700

Data Index: 6060139 (Open Web Text)

Max Activating Token Index: 193

Text #2

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.3352. Min Act: -0.1700

Data Index: 6060137 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2772. Min Act: -0.1700

Data Index: 4728173 (Open Web Text)

Max Activating Token Index: 618

Text #4

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2780. Min Act: -0.1700

Data Index: 7179455 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2780. Min Act: -0.1700

Data Index: 210005 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2488. Min Act: -0.1700

Data Index: 3617946 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2426. Min Act: -0.1700

Data Index: 2864957 (Open Web Text)

Max Activating Token Index: 991

Text #8

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2540. Min Act: -0.1700

Data Index: 6060138 (Open Web Text)

Max Activating Token Index: 271

Text #9

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2523. Min Act: -0.1700

Data Index: 6060136 (Open Web Text)

Max Activating Token Index: 977

Text #10

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2598. Min Act: -0.1700

Data Index: 6060140 (Open Web Text)

Max Activating Token Index: 245

Text #11

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2477. Min Act: -0.1700

Data Index: 7754532 (Open Web Text)

Max Activating Token Index: 1003

Text #12

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.2129. Min Act: -0.1700

Data Index: 4358466 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.1741. Min Act: -0.1700

Data Index: 7754533 (Open Web Text)

Max Activating Token Index: 966

Text #14

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.1610. Min Act: -0.1700

Data Index: 3574769 (Open Web Text)

Max Activating Token Index: 665

Text #15

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.1651. Min Act: -0.1700

Data Index: 2755430 (Open Web Text)

Max Activating Token Index: 877

Text #16

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.1884. Min Act: -0.1700

Data Index: 3574772 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.1701. Min Act: -0.1700

Data Index: 6938830 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.1919. Min Act: -0.1700

Data Index: 210007 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 5.3658. Min Range: -5.3658

Max Act: 5.1531. Min Act: -0.1700

Data Index: 7754531 (Open Web Text)

Max Activating Token Index: 558