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

Dataset: Open Web Text

Neuron 640 in Layer 1

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: 4.1559. Min Range: -4.1559

Max Act: 4.1559. Min Act: -0.1700

Data Index: 2254899 (Open Web Text)

Max Activating Token Index: 181

Text #1

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.1484. Min Act: -0.1700

Data Index: 6702986 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.1471. Min Act: -0.1700

Data Index: 4083697 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.1465. Min Act: -0.1700

Data Index: 4257800 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.1020. Min Act: -0.1700

Data Index: 4289769 (Open Web Text)

Max Activating Token Index: 325

Text #5

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.1277. Min Act: -0.1700

Data Index: 1767989 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0855. Min Act: -0.1700

Data Index: 6379585 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0665. Min Act: -0.1700

Data Index: 1153310 (Open Web Text)

Max Activating Token Index: 350

Text #8

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0714. Min Act: -0.1700

Data Index: 1190788 (Open Web Text)

Max Activating Token Index: 363

Text #9

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0735. Min Act: -0.1700

Data Index: 8114222 (Open Web Text)

Max Activating Token Index: 132

Text #10

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0670. Min Act: -0.1700

Data Index: 3687029 (Open Web Text)

Max Activating Token Index: 422

Text #11

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.1033. Min Act: -0.1700

Data Index: 4971962 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0908. Min Act: -0.1700

Data Index: 5276919 (Open Web Text)

Max Activating Token Index: 223

Text #13

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0408. Min Act: -0.1700

Data Index: 2165675 (Open Web Text)

Max Activating Token Index: 569

Text #14

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0491. Min Act: -0.1700

Data Index: 5809698 (Open Web Text)

Max Activating Token Index: 333

Text #15

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0554. Min Act: -0.1700

Data Index: 5599413 (Open Web Text)

Max Activating Token Index: 95

Text #16

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0562. Min Act: -0.1700

Data Index: 3123006 (Open Web Text)

Max Activating Token Index: 274

Text #17

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0399. Min Act: -0.1700

Data Index: 1911453 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0290. Min Act: -0.1700

Data Index: 3094653 (Open Web Text)

Max Activating Token Index: 336

Text #19

Max Range: 4.1559. Min Range: -4.1559

Max Act: 4.0402. Min Act: -0.1700

Data Index: 4459048 (Open Web Text)

Max Activating Token Index: 3