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

Dataset: Open Web Text

Neuron 91 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: 1.3533. Min Range: -1.3533

Max Act: 1.3533. Min Act: -0.1700

Data Index: 4819109 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.3060. Min Act: -0.1700

Data Index: 7803370 (Open Web Text)

Max Activating Token Index: 355

Text #2

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2975. Min Act: -0.1700

Data Index: 7330699 (Open Web Text)

Max Activating Token Index: 52

Text #3

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2841. Min Act: -0.1700

Data Index: 7144790 (Open Web Text)

Max Activating Token Index: 277

Text #4

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2783. Min Act: -0.1699

Data Index: 7074287 (Open Web Text)

Max Activating Token Index: 237

Text #5

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2750. Min Act: -0.1699

Data Index: 731973 (Open Web Text)

Max Activating Token Index: 402

Text #6

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2659. Min Act: -0.1700

Data Index: 8424063 (Open Web Text)

Max Activating Token Index: 253

Text #7

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2717. Min Act: -0.1700

Data Index: 2609810 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2639. Min Act: -0.1700

Data Index: 8424068 (Open Web Text)

Max Activating Token Index: 742

Text #9

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2659. Min Act: -0.1700

Data Index: 4677079 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2647. Min Act: -0.1693

Data Index: 6792960 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2600. Min Act: -0.1700

Data Index: 7144793 (Open Web Text)

Max Activating Token Index: 526

Text #12

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2567. Min Act: -0.1700

Data Index: 6061297 (Open Web Text)

Max Activating Token Index: 816

Text #13

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2556. Min Act: -0.1700

Data Index: 7144791 (Open Web Text)

Max Activating Token Index: 562

Text #14

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2562. Min Act: -0.1700

Data Index: 305428 (Open Web Text)

Max Activating Token Index: 844

Text #15

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2472. Min Act: -0.1700

Data Index: 7144795 (Open Web Text)

Max Activating Token Index: 799

Text #16

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2519. Min Act: -0.1700

Data Index: 7144789 (Open Web Text)

Max Activating Token Index: 690

Text #17

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2548. Min Act: -0.1700

Data Index: 7144794 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2525. Min Act: -0.1700

Data Index: 6988291 (Open Web Text)

Max Activating Token Index: 231

Text #19

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2628. Min Act: -0.1699

Data Index: 344368 (Open Web Text)

Max Activating Token Index: 629