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

Dataset: Open Web Text

Neuron 1708 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: 1.2285. Min Range: -1.2285

Max Act: 1.2285. Min Act: -0.1700

Data Index: 3173231 (Open Web Text)

Max Activating Token Index: 435

Text #1

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.1612. Min Act: -0.1700

Data Index: 5955306 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.1664. Min Act: -0.1700

Data Index: 6333442 (Open Web Text)

Max Activating Token Index: 410

Text #3

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.1638. Min Act: -0.1700

Data Index: 5519728 (Open Web Text)

Max Activating Token Index: 429

Text #4

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.1640. Min Act: -0.1700

Data Index: 2163461 (Open Web Text)

Max Activating Token Index: 430

Text #5

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0991. Min Act: -0.1700

Data Index: 5304010 (Open Web Text)

Max Activating Token Index: 400

Text #6

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0665. Min Act: -0.1700

Data Index: 7829898 (Open Web Text)

Max Activating Token Index: 441

Text #7

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0720. Min Act: -0.1700

Data Index: 7125924 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0458. Min Act: -0.1700

Data Index: 7245505 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0284. Min Act: -0.1699

Data Index: 2672891 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0225. Min Act: -0.1700

Data Index: 3132497 (Open Web Text)

Max Activating Token Index: 456

Text #11

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0072. Min Act: -0.1700

Data Index: 5447646 (Open Web Text)

Max Activating Token Index: 417

Text #12

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0085. Min Act: -0.1700

Data Index: 8436298 (Open Web Text)

Max Activating Token Index: 417

Text #13

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9774. Min Act: -0.1700

Data Index: 5454706 (Open Web Text)

Max Activating Token Index: 435

Text #14

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9850. Min Act: -0.1700

Data Index: 8162051 (Open Web Text)

Max Activating Token Index: 448

Text #15

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9847. Min Act: -0.1700

Data Index: 3760976 (Open Web Text)

Max Activating Token Index: 412

Text #16

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9768. Min Act: -0.1700

Data Index: 8684261 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9709. Min Act: -0.1700

Data Index: 8741424 (Open Web Text)

Max Activating Token Index: 439

Text #18

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9734. Min Act: -0.1700

Data Index: 6048278 (Open Web Text)

Max Activating Token Index: 444

Text #19

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9647. Min Act: -0.1700

Data Index: 6343204 (Open Web Text)

Max Activating Token Index: 417