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

Dataset: Open Web Text

Neuron 682 in Layer 5

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: 4.9680. Min Range: -4.9680

Max Act: 4.9680. Min Act: -0.1700

Data Index: 4793313 (Open Web Text)

Max Activating Token Index: 174

Text #1

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.9166. Min Act: -0.1700

Data Index: 1263099 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.8332. Min Act: -0.1700

Data Index: 6417152 (Open Web Text)

Max Activating Token Index: 114

Text #3

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.8293. Min Act: -0.1700

Data Index: 3356014 (Open Web Text)

Max Activating Token Index: 957

Text #4

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.7938. Min Act: -0.1700

Data Index: 4827349 (Open Web Text)

Max Activating Token Index: 123

Text #5

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.7225. Min Act: -0.1700

Data Index: 6827989 (Open Web Text)

Max Activating Token Index: 575

Text #6

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6996. Min Act: -0.1700

Data Index: 5647952 (Open Web Text)

Max Activating Token Index: 648

Text #7

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.7193. Min Act: -0.1700

Data Index: 8612207 (Open Web Text)

Max Activating Token Index: 143

Text #8

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.7008. Min Act: -0.1700

Data Index: 869406 (Open Web Text)

Max Activating Token Index: 608

Text #9

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6995. Min Act: -0.1700

Data Index: 1584202 (Open Web Text)

Max Activating Token Index: 733

Text #10

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6502. Min Act: -0.1700

Data Index: 2422242 (Open Web Text)

Max Activating Token Index: 810

Text #11

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6923. Min Act: -0.1700

Data Index: 5914133 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6315. Min Act: -0.1700

Data Index: 3347003 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6938. Min Act: -0.1700

Data Index: 4009583 (Open Web Text)

Max Activating Token Index: 706

Text #14

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6400. Min Act: -0.1700

Data Index: 7541961 (Open Web Text)

Max Activating Token Index: 822

Text #15

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6439. Min Act: -0.1700

Data Index: 1766956 (Open Web Text)

Max Activating Token Index: 623

Text #16

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6550. Min Act: -0.1700

Data Index: 3689424 (Open Web Text)

Max Activating Token Index: 391

Text #17

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.6180. Min Act: -0.1700

Data Index: 1252369 (Open Web Text)

Max Activating Token Index: 790

Text #18

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.5907. Min Act: -0.1700

Data Index: 685932 (Open Web Text)

Max Activating Token Index: 606

Text #19

Max Range: 4.9680. Min Range: -4.9680

Max Act: 4.5890. Min Act: -0.1700

Data Index: 291828 (Open Web Text)

Max Activating Token Index: 306