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

Dataset: Open Web Text

Neuron 678 in Layer 5

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: 4.3770. Min Range: -4.3770

Max Act: 4.3770. Min Act: -0.1700

Data Index: 6559802 (Open Web Text)

Max Activating Token Index: 524

Text #1

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.3514. Min Act: -0.1700

Data Index: 5457554 (Open Web Text)

Max Activating Token Index: 76

Text #2

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.3520. Min Act: -0.1700

Data Index: 5907703 (Open Web Text)

Max Activating Token Index: 249

Text #3

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.3315. Min Act: -0.1700

Data Index: 7493799 (Open Web Text)

Max Activating Token Index: 114

Text #4

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.3136. Min Act: -0.1700

Data Index: 207535 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.3218. Min Act: -0.1700

Data Index: 3106591 (Open Web Text)

Max Activating Token Index: 228

Text #6

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.3098. Min Act: -0.1700

Data Index: 2342987 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2925. Min Act: -0.1700

Data Index: 3514552 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2780. Min Act: -0.1700

Data Index: 6276845 (Open Web Text)

Max Activating Token Index: 40

Text #9

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2940. Min Act: -0.1700

Data Index: 7629720 (Open Web Text)

Max Activating Token Index: 374

Text #10

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2898. Min Act: -0.1700

Data Index: 6797439 (Open Web Text)

Max Activating Token Index: 355

Text #11

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2896. Min Act: -0.1700

Data Index: 744142 (Open Web Text)

Max Activating Token Index: 392

Text #12

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2679. Min Act: -0.1700

Data Index: 7118134 (Open Web Text)

Max Activating Token Index: 845

Text #13

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2981. Min Act: -0.1700

Data Index: 4300537 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2970. Min Act: -0.1700

Data Index: 4427640 (Open Web Text)

Max Activating Token Index: 927

Text #15

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2802. Min Act: -0.1700

Data Index: 7588856 (Open Web Text)

Max Activating Token Index: 638

Text #16

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2447. Min Act: -0.1700

Data Index: 6396524 (Open Web Text)

Max Activating Token Index: 260

Text #17

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2498. Min Act: -0.1700

Data Index: 3817542 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2257. Min Act: -0.1700

Data Index: 2701569 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 4.3770. Min Range: -4.3770

Max Act: 4.2632. Min Act: -0.1700

Data Index: 977499 (Open Web Text)

Max Activating Token Index: 386