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

Dataset: Open Web Text

Neuron 387 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: 1.8776. Min Range: -1.8776

Max Act: 1.8776. Min Act: -0.1700

Data Index: 2033477 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.8776. Min Act: -0.1699

Data Index: 4354272 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.8399. Min Act: -0.1700

Data Index: 4732106 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.8324. Min Act: -0.1700

Data Index: 2033475 (Open Web Text)

Max Activating Token Index: 180

Text #4

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.8299. Min Act: -0.1700

Data Index: 8063036 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.8096. Min Act: -0.1700

Data Index: 545920 (Open Web Text)

Max Activating Token Index: 394

Text #6

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.8033. Min Act: -0.1699

Data Index: 2033467 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7946. Min Act: -0.1700

Data Index: 8362282 (Open Web Text)

Max Activating Token Index: 671

Text #8

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.8013. Min Act: -0.1700

Data Index: 8265452 (Open Web Text)

Max Activating Token Index: 144

Text #9

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7781. Min Act: -0.1700

Data Index: 4841782 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7876. Min Act: -0.1700

Data Index: 3261483 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7902. Min Act: -0.1700

Data Index: 2780813 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7802. Min Act: -0.1700

Data Index: 2710432 (Open Web Text)

Max Activating Token Index: 336

Text #13

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7802. Min Act: -0.1700

Data Index: 379876 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7666. Min Act: -0.1700

Data Index: 7482590 (Open Web Text)

Max Activating Token Index: 325

Text #15

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7558. Min Act: -0.1700

Data Index: 1474577 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7585. Min Act: -0.1700

Data Index: 1991285 (Open Web Text)

Max Activating Token Index: 252

Text #17

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7549. Min Act: -0.1700

Data Index: 4041158 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7588. Min Act: -0.1700

Data Index: 1020965 (Open Web Text)

Max Activating Token Index: 254

Text #19

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7615. Min Act: -0.1700

Data Index: 2090057 (Open Web Text)

Max Activating Token Index: 47