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

Dataset: Open Web Text

Neuron 980 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: 1.5479. Min Range: -1.5479

Max Act: 1.5479. Min Act: -0.1700

Data Index: 5449691 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.5011. Min Act: -0.1700

Data Index: 6324928 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.4618. Min Act: -0.1700

Data Index: 5981044 (Open Web Text)

Max Activating Token Index: 879

Text #3

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.4477. Min Act: -0.1700

Data Index: 1512057 (Open Web Text)

Max Activating Token Index: 767

Text #4

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.4252. Min Act: -0.1700

Data Index: 4585419 (Open Web Text)

Max Activating Token Index: 423

Text #5

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.4209. Min Act: -0.1700

Data Index: 4503306 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.4045. Min Act: -0.1700

Data Index: 1645848 (Open Web Text)

Max Activating Token Index: 617

Text #7

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.4069. Min Act: -0.1700

Data Index: 4754274 (Open Web Text)

Max Activating Token Index: 78

Text #8

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3990. Min Act: -0.1700

Data Index: 5633857 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3843. Min Act: -0.1700

Data Index: 5407443 (Open Web Text)

Max Activating Token Index: 948

Text #10

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3833. Min Act: -0.1700

Data Index: 2273587 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.4005. Min Act: -0.1700

Data Index: 6324927 (Open Web Text)

Max Activating Token Index: 325

Text #12

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3748. Min Act: -0.1700

Data Index: 1559331 (Open Web Text)

Max Activating Token Index: 841

Text #13

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3878. Min Act: -0.1700

Data Index: 8219494 (Open Web Text)

Max Activating Token Index: 559

Text #14

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3781. Min Act: -0.1700

Data Index: 7958700 (Open Web Text)

Max Activating Token Index: 658

Text #15

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3815. Min Act: -0.1700

Data Index: 6213845 (Open Web Text)

Max Activating Token Index: 831

Text #16

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3824. Min Act: -0.1700

Data Index: 5867152 (Open Web Text)

Max Activating Token Index: 716

Text #17

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3822. Min Act: -0.1700

Data Index: 2829485 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3566. Min Act: -0.1700

Data Index: 2829486 (Open Web Text)

Max Activating Token Index: 242

Text #19

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3703. Min Act: -0.1700

Data Index: 5540667 (Open Web Text)

Max Activating Token Index: 998