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

Dataset: Open Web Text

Neuron 978 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: 3.8921. Min Range: -3.8921

Max Act: 3.8921. Min Act: -0.1700

Data Index: 2356422 (Open Web Text)

Max Activating Token Index: 596

Text #1

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.8730. Min Act: -0.1700

Data Index: 1030364 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.8774. Min Act: -0.1700

Data Index: 7076072 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.8361. Min Act: -0.1700

Data Index: 2339536 (Open Web Text)

Max Activating Token Index: 622

Text #4

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.8286. Min Act: -0.1700

Data Index: 4733755 (Open Web Text)

Max Activating Token Index: 367

Text #5

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.8338. Min Act: -0.1700

Data Index: 7576367 (Open Web Text)

Max Activating Token Index: 677

Text #6

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.8243. Min Act: -0.1700

Data Index: 6464607 (Open Web Text)

Max Activating Token Index: 195

Text #7

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7651. Min Act: -0.1700

Data Index: 4711492 (Open Web Text)

Max Activating Token Index: 106

Text #8

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7798. Min Act: -0.1700

Data Index: 1649896 (Open Web Text)

Max Activating Token Index: 583

Text #9

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7533. Min Act: -0.1700

Data Index: 734992 (Open Web Text)

Max Activating Token Index: 559

Text #10

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7486. Min Act: -0.1700

Data Index: 6336729 (Open Web Text)

Max Activating Token Index: 884

Text #11

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7798. Min Act: -0.1700

Data Index: 4935868 (Open Web Text)

Max Activating Token Index: 381

Text #12

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7632. Min Act: -0.1700

Data Index: 4002634 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7568. Min Act: -0.1700

Data Index: 4848179 (Open Web Text)

Max Activating Token Index: 765

Text #14

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7389. Min Act: -0.1700

Data Index: 2162395 (Open Web Text)

Max Activating Token Index: 518

Text #15

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7587. Min Act: -0.1700

Data Index: 5521827 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7685. Min Act: -0.1700

Data Index: 3852830 (Open Web Text)

Max Activating Token Index: 581

Text #17

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7604. Min Act: -0.1700

Data Index: 3560256 (Open Web Text)

Max Activating Token Index: 1000

Text #18

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7643. Min Act: -0.1700

Data Index: 895148 (Open Web Text)

Max Activating Token Index: 89

Text #19

Max Range: 3.8921. Min Range: -3.8921

Max Act: 3.7700. Min Act: -0.1700

Data Index: 4244298 (Open Web Text)

Max Activating Token Index: 998