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

Dataset: Open Web Text

Neuron 117 in Layer 0

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: 1.8753. Min Range: -1.8753

Max Act: 1.8753. Min Act: -0.0832

Data Index: 6990145 (Open Web Text)

Max Activating Token Index: 526

Text #1

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8312. Min Act: -0.0849

Data Index: 4104127 (Open Web Text)

Max Activating Token Index: 826

Text #2

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8255. Min Act: -0.1314

Data Index: 4816050 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8070. Min Act: -0.1641

Data Index: 7424227 (Open Web Text)

Max Activating Token Index: 624

Text #4

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7957. Min Act: -0.1507

Data Index: 106686 (Open Web Text)

Max Activating Token Index: 515

Text #5

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7754. Min Act: -0.1520

Data Index: 8586857 (Open Web Text)

Max Activating Token Index: 647

Text #6

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7920. Min Act: -0.0991

Data Index: 3186500 (Open Web Text)

Max Activating Token Index: 757

Text #7

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7830. Min Act: -0.1642

Data Index: 8812128 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7849. Min Act: -0.1442

Data Index: 291843 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7732. Min Act: -0.1674

Data Index: 116810 (Open Web Text)

Max Activating Token Index: 771

Text #10

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7693. Min Act: -0.1251

Data Index: 5335785 (Open Web Text)

Max Activating Token Index: 542

Text #11

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7640. Min Act: -0.1360

Data Index: 1937705 (Open Web Text)

Max Activating Token Index: 393

Text #12

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7595. Min Act: -0.0618

Data Index: 4314598 (Open Web Text)

Max Activating Token Index: 527

Text #13

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7623. Min Act: -0.1044

Data Index: 3782185 (Open Web Text)

Max Activating Token Index: 591

Text #14

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7557. Min Act: -0.1700

Data Index: 5142237 (Open Web Text)

Max Activating Token Index: 456

Text #15

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7676. Min Act: -0.1676

Data Index: 5096339 (Open Web Text)

Max Activating Token Index: 691

Text #16

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7612. Min Act: -0.1277

Data Index: 2324849 (Open Web Text)

Max Activating Token Index: 682

Text #17

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7593. Min Act: -0.1324

Data Index: 6650 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7658. Min Act: -0.1611

Data Index: 2801367 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7545. Min Act: -0.1269

Data Index: 3378034 (Open Web Text)

Max Activating Token Index: 518