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

Dataset: Open Web Text

Neuron 478 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: 2.4927. Min Range: -2.4927

Max Act: 2.4792. Min Act: -0.1700

Data Index: 8765058 (Open Web Text)

Max Activating Token Index: 865

Text #1

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4767. Min Act: -0.1700

Data Index: 1513213 (Open Web Text)

Max Activating Token Index: 398

Text #2

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4927. Min Act: -0.1700

Data Index: 6730719 (Open Web Text)

Max Activating Token Index: 685

Text #3

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4699. Min Act: -0.1700

Data Index: 5729745 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4789. Min Act: -0.1700

Data Index: 6695632 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4427. Min Act: -0.1700

Data Index: 1554097 (Open Web Text)

Max Activating Token Index: 498

Text #6

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4411. Min Act: -0.1700

Data Index: 1291105 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4544. Min Act: -0.1700

Data Index: 2104991 (Open Web Text)

Max Activating Token Index: 579

Text #8

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4311. Min Act: -0.1700

Data Index: 8765052 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4290. Min Act: -0.1700

Data Index: 4389545 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4327. Min Act: -0.1700

Data Index: 7952163 (Open Web Text)

Max Activating Token Index: 812

Text #11

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4181. Min Act: -0.1700

Data Index: 6508361 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4244. Min Act: -0.1700

Data Index: 1505067 (Open Web Text)

Max Activating Token Index: 531

Text #13

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4211. Min Act: -0.1700

Data Index: 4111056 (Open Web Text)

Max Activating Token Index: 354

Text #14

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4169. Min Act: -0.1700

Data Index: 8802378 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4054. Min Act: -0.1700

Data Index: 7138576 (Open Web Text)

Max Activating Token Index: 462

Text #16

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4135. Min Act: -0.1700

Data Index: 6899252 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4201. Min Act: -0.1700

Data Index: 6433596 (Open Web Text)

Max Activating Token Index: 642

Text #18

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4075. Min Act: -0.1700

Data Index: 6864642 (Open Web Text)

Max Activating Token Index: 763

Text #19

Max Range: 2.4927. Min Range: -2.4927

Max Act: 2.4096. Min Act: -0.1700

Data Index: 7952164 (Open Web Text)

Max Activating Token Index: 897