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

Dataset: Open Web Text

Neuron 1449 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: 1.3866. Min Range: -1.3866

Max Act: 1.3866. Min Act: -0.1700

Data Index: 4613037 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.3478. Min Act: -0.1698

Data Index: 4266173 (Open Web Text)

Max Activating Token Index: 105

Text #2

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.3141. Min Act: -0.1697

Data Index: 3356789 (Open Web Text)

Max Activating Token Index: 777

Text #3

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.3094. Min Act: -0.1699

Data Index: 3737197 (Open Web Text)

Max Activating Token Index: 748

Text #4

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.3110. Min Act: -0.1699

Data Index: 3699054 (Open Web Text)

Max Activating Token Index: 317

Text #5

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2814. Min Act: -0.1694

Data Index: 6798782 (Open Web Text)

Max Activating Token Index: 186

Text #6

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2845. Min Act: -0.1700

Data Index: 6947672 (Open Web Text)

Max Activating Token Index: 938

Text #7

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2876. Min Act: -0.1700

Data Index: 5209367 (Open Web Text)

Max Activating Token Index: 548

Text #8

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2790. Min Act: -0.1700

Data Index: 3302909 (Open Web Text)

Max Activating Token Index: 232

Text #9

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2779. Min Act: -0.1676

Data Index: 540270 (Open Web Text)

Max Activating Token Index: 853

Text #10

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2599. Min Act: -0.1700

Data Index: 8268900 (Open Web Text)

Max Activating Token Index: 379

Text #11

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2502. Min Act: -0.1700

Data Index: 8338248 (Open Web Text)

Max Activating Token Index: 831

Text #12

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2514. Min Act: -0.1700

Data Index: 7195940 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2564. Min Act: -0.1700

Data Index: 3626909 (Open Web Text)

Max Activating Token Index: 139

Text #14

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2522. Min Act: -0.1696

Data Index: 4500156 (Open Web Text)

Max Activating Token Index: 784

Text #15

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2453. Min Act: -0.1694

Data Index: 6195709 (Open Web Text)

Max Activating Token Index: 835

Text #16

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2352. Min Act: -0.1700

Data Index: 4600872 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2381. Min Act: -0.1698

Data Index: 7506866 (Open Web Text)

Max Activating Token Index: 701

Text #18

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2331. Min Act: -0.1700

Data Index: 3013124 (Open Web Text)

Max Activating Token Index: 614

Text #19

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.2334. Min Act: -0.1680

Data Index: 4946518 (Open Web Text)

Max Activating Token Index: 362