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

Dataset: Open Web Text

Neuron 510 in Layer 0

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: 4.8632. Min Range: -4.8632

Max Act: 4.8632. Min Act: -0.1700

Data Index: 5323810 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.7361. Min Act: -0.1700

Data Index: 5797482 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.7222. Min Act: -0.1700

Data Index: 2909517 (Open Web Text)

Max Activating Token Index: 94

Text #3

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.6981. Min Act: -0.1700

Data Index: 6726335 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.6949. Min Act: -0.1700

Data Index: 901074 (Open Web Text)

Max Activating Token Index: 108

Text #5

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.6802. Min Act: -0.1700

Data Index: 1693625 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.6521. Min Act: -0.1700

Data Index: 3665961 (Open Web Text)

Max Activating Token Index: 41

Text #7

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.6633. Min Act: -0.1700

Data Index: 1710514 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.6251. Min Act: -0.1700

Data Index: 3860660 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.6028. Min Act: -0.1700

Data Index: 1558494 (Open Web Text)

Max Activating Token Index: 679

Text #10

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.6066. Min Act: -0.1700

Data Index: 1704490 (Open Web Text)

Max Activating Token Index: 45

Text #11

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.6142. Min Act: -0.1700

Data Index: 4643887 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.5912. Min Act: -0.1700

Data Index: 782694 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.5778. Min Act: -0.1700

Data Index: 5988985 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.5807. Min Act: -0.1700

Data Index: 2168000 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.5897. Min Act: -0.1700

Data Index: 3232340 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.5512. Min Act: -0.1700

Data Index: 6024387 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.5406. Min Act: -0.1700

Data Index: 2849780 (Open Web Text)

Max Activating Token Index: 44

Text #18

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.5084. Min Act: -0.1700

Data Index: 1333667 (Open Web Text)

Max Activating Token Index: 60

Text #19

Max Range: 4.8632. Min Range: -4.8632

Max Act: 4.5124. Min Act: -0.1700

Data Index: 260309 (Open Web Text)

Max Activating Token Index: 270