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

Dataset: Open Web Text

Neuron 2121 in Layer 4

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: 3.4680. Min Range: -3.4680

Max Act: 3.4680. Min Act: -0.1700

Data Index: 7973109 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.4513. Min Act: -0.1700

Data Index: 2709972 (Open Web Text)

Max Activating Token Index: 571

Text #2

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.4095. Min Act: -0.1700

Data Index: 8347544 (Open Web Text)

Max Activating Token Index: 987

Text #3

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.4002. Min Act: -0.1700

Data Index: 6074058 (Open Web Text)

Max Activating Token Index: 607

Text #4

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3958. Min Act: -0.1700

Data Index: 2459049 (Open Web Text)

Max Activating Token Index: 134

Text #5

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3753. Min Act: -0.1700

Data Index: 6864346 (Open Web Text)

Max Activating Token Index: 664

Text #6

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3517. Min Act: -0.1700

Data Index: 183740 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3696. Min Act: -0.1700

Data Index: 6551697 (Open Web Text)

Max Activating Token Index: 260

Text #8

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3769. Min Act: -0.1700

Data Index: 4858250 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3783. Min Act: -0.1700

Data Index: 6081479 (Open Web Text)

Max Activating Token Index: 331

Text #10

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3677. Min Act: -0.1700

Data Index: 6957241 (Open Web Text)

Max Activating Token Index: 345

Text #11

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3787. Min Act: -0.1700

Data Index: 4368403 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3560. Min Act: -0.1700

Data Index: 163587 (Open Web Text)

Max Activating Token Index: 249

Text #13

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3672. Min Act: -0.1700

Data Index: 2602166 (Open Web Text)

Max Activating Token Index: 587

Text #14

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3566. Min Act: -0.1700

Data Index: 5296261 (Open Web Text)

Max Activating Token Index: 727

Text #15

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3581. Min Act: -0.1700

Data Index: 6164443 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3652. Min Act: -0.1700

Data Index: 1082001 (Open Web Text)

Max Activating Token Index: 531

Text #17

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3914. Min Act: -0.1700

Data Index: 6669913 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3525. Min Act: -0.1700

Data Index: 435900 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 3.4680. Min Range: -3.4680

Max Act: 3.3574. Min Act: -0.1700

Data Index: 3231299 (Open Web Text)

Max Activating Token Index: 76