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

Dataset: Open Web Text

Neuron 258 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: 3.0780. Min Range: -3.0780

Max Act: 3.0780. Min Act: -0.1700

Data Index: 7762211 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.0780. Min Range: -3.0780

Max Act: 3.0097. Min Act: -0.1700

Data Index: 4499644 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.0780. Min Range: -3.0780

Max Act: 3.0086. Min Act: -0.1700

Data Index: 7738361 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9900. Min Act: -0.1700

Data Index: 1370966 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9935. Min Act: -0.1700

Data Index: 8292878 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9822. Min Act: -0.1700

Data Index: 1474077 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9791. Min Act: -0.1700

Data Index: 3518766 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9565. Min Act: -0.1700

Data Index: 1884852 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9683. Min Act: -0.1700

Data Index: 2109171 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9503. Min Act: -0.1700

Data Index: 6110495 (Open Web Text)

Max Activating Token Index: 331

Text #10

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9406. Min Act: -0.1700

Data Index: 1820333 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9300. Min Act: -0.1700

Data Index: 6331193 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9278. Min Act: -0.1700

Data Index: 6258207 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9282. Min Act: -0.1700

Data Index: 6214618 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9355. Min Act: -0.1700

Data Index: 8297444 (Open Web Text)

Max Activating Token Index: 269

Text #15

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9376. Min Act: -0.1700

Data Index: 270688 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9360. Min Act: -0.1700

Data Index: 3653867 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9338. Min Act: -0.1700

Data Index: 1812503 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9261. Min Act: -0.1700

Data Index: 6890380 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9243. Min Act: -0.1700

Data Index: 6657820 (Open Web Text)

Max Activating Token Index: 6