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

Dataset: Open Web Text

Neuron 2784 in Layer 6

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: 3.1490. Min Range: -3.1490

Max Act: 3.1490. Min Act: -0.1700

Data Index: 1694123 (Open Web Text)

Max Activating Token Index: 496

Text #1

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.9564. Min Act: -0.1700

Data Index: 5726496 (Open Web Text)

Max Activating Token Index: 214

Text #2

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.9462. Min Act: -0.1700

Data Index: 7782542 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.9080. Min Act: -0.1700

Data Index: 977958 (Open Web Text)

Max Activating Token Index: 745

Text #4

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8936. Min Act: -0.1700

Data Index: 2396500 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8936. Min Act: -0.1700

Data Index: 392168 (Open Web Text)

Max Activating Token Index: 565

Text #6

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8856. Min Act: -0.1700

Data Index: 5415748 (Open Web Text)

Max Activating Token Index: 666

Text #7

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8695. Min Act: -0.1700

Data Index: 8670501 (Open Web Text)

Max Activating Token Index: 694

Text #8

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8690. Min Act: -0.1700

Data Index: 2069727 (Open Web Text)

Max Activating Token Index: 646

Text #9

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8983. Min Act: -0.1700

Data Index: 156177 (Open Web Text)

Max Activating Token Index: 410

Text #10

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8488. Min Act: -0.1700

Data Index: 204430 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8684. Min Act: -0.1700

Data Index: 5813286 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8365. Min Act: -0.1700

Data Index: 2753755 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8522. Min Act: -0.1700

Data Index: 4647399 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8413. Min Act: -0.1700

Data Index: 1842233 (Open Web Text)

Max Activating Token Index: 850

Text #15

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8447. Min Act: -0.1700

Data Index: 2138932 (Open Web Text)

Max Activating Token Index: 427

Text #16

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8057. Min Act: -0.1700

Data Index: 7305096 (Open Web Text)

Max Activating Token Index: 928

Text #17

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8175. Min Act: -0.1700

Data Index: 1478295 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8168. Min Act: -0.1700

Data Index: 1949644 (Open Web Text)

Max Activating Token Index: 114

Text #19

Max Range: 3.1490. Min Range: -3.1490

Max Act: 2.8153. Min Act: -0.1700

Data Index: 2824043 (Open Web Text)

Max Activating Token Index: 919