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

Dataset: Open Web Text

Neuron 698 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: 3.3549. Min Range: -3.3549

Max Act: 3.3549. Min Act: -0.1700

Data Index: 6615203 (Open Web Text)

Max Activating Token Index: 393

Text #1

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.2465. Min Act: -0.1700

Data Index: 432309 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.2393. Min Act: -0.1700

Data Index: 5290360 (Open Web Text)

Max Activating Token Index: 608

Text #3

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.2684. Min Act: -0.1700

Data Index: 1497150 (Open Web Text)

Max Activating Token Index: 455

Text #4

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.2198. Min Act: -0.1700

Data Index: 6234563 (Open Web Text)

Max Activating Token Index: 962

Text #5

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.2027. Min Act: -0.1700

Data Index: 6360908 (Open Web Text)

Max Activating Token Index: 921

Text #6

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1935. Min Act: -0.1700

Data Index: 8250099 (Open Web Text)

Max Activating Token Index: 951

Text #7

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1741. Min Act: -0.1700

Data Index: 4696748 (Open Web Text)

Max Activating Token Index: 765

Text #8

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1993. Min Act: -0.1700

Data Index: 5065181 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1834. Min Act: -0.1700

Data Index: 4050813 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1725. Min Act: -0.1700

Data Index: 4237874 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1759. Min Act: -0.1700

Data Index: 1577347 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1543. Min Act: -0.1700

Data Index: 7943848 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1514. Min Act: -0.1700

Data Index: 8571105 (Open Web Text)

Max Activating Token Index: 250

Text #14

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1712. Min Act: -0.1700

Data Index: 6288289 (Open Web Text)

Max Activating Token Index: 675

Text #15

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1276. Min Act: -0.1700

Data Index: 5362433 (Open Web Text)

Max Activating Token Index: 605

Text #16

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1353. Min Act: -0.1700

Data Index: 2836659 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1163. Min Act: -0.1700

Data Index: 8373002 (Open Web Text)

Max Activating Token Index: 794

Text #18

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1146. Min Act: -0.1700

Data Index: 6338792 (Open Web Text)

Max Activating Token Index: 495

Text #19

Max Range: 3.3549. Min Range: -3.3549

Max Act: 3.1435. Min Act: -0.1700

Data Index: 386742 (Open Web Text)

Max Activating Token Index: 546