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

Dataset: Open Web Text

Neuron 2482 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: 4.6595. Min Range: -4.6595

Max Act: 4.6595. Min Act: -0.1700

Data Index: 2878658 (Open Web Text)

Max Activating Token Index: 110

Text #1

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.6056. Min Act: -0.1700

Data Index: 5342634 (Open Web Text)

Max Activating Token Index: 165

Text #2

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.5880. Min Act: -0.1700

Data Index: 6221350 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.5509. Min Act: -0.1700

Data Index: 4170004 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.5664. Min Act: -0.1700

Data Index: 6552507 (Open Web Text)

Max Activating Token Index: 744

Text #5

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.5617. Min Act: -0.1700

Data Index: 5193256 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4840. Min Act: -0.1700

Data Index: 8484576 (Open Web Text)

Max Activating Token Index: 141

Text #7

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4872. Min Act: -0.1700

Data Index: 1890308 (Open Web Text)

Max Activating Token Index: 559

Text #8

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4960. Min Act: -0.1700

Data Index: 6958384 (Open Web Text)

Max Activating Token Index: 383

Text #9

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4945. Min Act: -0.1700

Data Index: 7993690 (Open Web Text)

Max Activating Token Index: 80

Text #10

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.5006. Min Act: -0.1700

Data Index: 5848504 (Open Web Text)

Max Activating Token Index: 83

Text #11

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4570. Min Act: -0.1700

Data Index: 6196096 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4464. Min Act: -0.1700

Data Index: 1867691 (Open Web Text)

Max Activating Token Index: 603

Text #13

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4822. Min Act: -0.1700

Data Index: 7061099 (Open Web Text)

Max Activating Token Index: 347

Text #14

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4455. Min Act: -0.1700

Data Index: 8218999 (Open Web Text)

Max Activating Token Index: 49

Text #15

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4296. Min Act: -0.1700

Data Index: 5668464 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4382. Min Act: -0.1700

Data Index: 1463018 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4053. Min Act: -0.1700

Data Index: 4385448 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.4080. Min Act: -0.1700

Data Index: 6300782 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 4.6595. Min Range: -4.6595

Max Act: 4.3942. Min Act: -0.1700

Data Index: 4729324 (Open Web Text)

Max Activating Token Index: 426