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

Dataset: Open Web Text

Neuron 1117 in Layer 4

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: 2.7506. Min Range: -2.7506

Max Act: 2.7506. Min Act: -0.1700

Data Index: 423436 (Open Web Text)

Max Activating Token Index: 618

Text #1

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6946. Min Act: -0.1700

Data Index: 2052952 (Open Web Text)

Max Activating Token Index: 367

Text #2

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6773. Min Act: -0.1700

Data Index: 118579 (Open Web Text)

Max Activating Token Index: 337

Text #3

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6667. Min Act: -0.1700

Data Index: 4578416 (Open Web Text)

Max Activating Token Index: 688

Text #4

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6480. Min Act: -0.1699

Data Index: 1343718 (Open Web Text)

Max Activating Token Index: 28

Text #5

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6484. Min Act: -0.1700

Data Index: 8823367 (Open Web Text)

Max Activating Token Index: 696

Text #6

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6924. Min Act: -0.1700

Data Index: 6784285 (Open Web Text)

Max Activating Token Index: 426

Text #7

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6430. Min Act: -0.1691

Data Index: 8569635 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6501. Min Act: -0.1700

Data Index: 3622487 (Open Web Text)

Max Activating Token Index: 513

Text #9

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6467. Min Act: -0.1700

Data Index: 348363 (Open Web Text)

Max Activating Token Index: 29

Text #10

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6476. Min Act: -0.1700

Data Index: 54697 (Open Web Text)

Max Activating Token Index: 500

Text #11

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6307. Min Act: -0.1690

Data Index: 8068926 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6075. Min Act: -0.1700

Data Index: 7928530 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6003. Min Act: -0.1700

Data Index: 2076881 (Open Web Text)

Max Activating Token Index: 755

Text #14

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.5988. Min Act: -0.1700

Data Index: 5352377 (Open Web Text)

Max Activating Token Index: 927

Text #15

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.5861. Min Act: -0.1700

Data Index: 4972427 (Open Web Text)

Max Activating Token Index: 727

Text #16

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.6139. Min Act: -0.1700

Data Index: 5151701 (Open Web Text)

Max Activating Token Index: 644

Text #17

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.5923. Min Act: -0.1700

Data Index: 296025 (Open Web Text)

Max Activating Token Index: 845

Text #18

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.5854. Min Act: -0.1700

Data Index: 7271393 (Open Web Text)

Max Activating Token Index: 33

Text #19

Max Range: 2.7506. Min Range: -2.7506

Max Act: 2.5923. Min Act: -0.1698

Data Index: 1343738 (Open Web Text)

Max Activating Token Index: 26