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

Dataset: Open Web Text

Neuron 1118 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: 4.0633. Min Range: -4.0633

Max Act: 4.0633. Min Act: -0.1700

Data Index: 6052027 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.0633. Min Range: -4.0633

Max Act: 4.0209. Min Act: -0.1700

Data Index: 5524179 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.9451. Min Act: -0.1700

Data Index: 7749864 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.8544. Min Act: -0.1700

Data Index: 3650448 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.7954. Min Act: -0.1700

Data Index: 3264006 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.8059. Min Act: -0.1700

Data Index: 5807049 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.7978. Min Act: -0.1700

Data Index: 271968 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.7582. Min Act: -0.1700

Data Index: 5856326 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.7582. Min Act: -0.1700

Data Index: 598215 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.7377. Min Act: -0.1700

Data Index: 735440 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.7164. Min Act: -0.1700

Data Index: 584290 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.7235. Min Act: -0.1700

Data Index: 7374336 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.7265. Min Act: -0.1700

Data Index: 6899363 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.7233. Min Act: -0.1700

Data Index: 345853 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.6721. Min Act: -0.1700

Data Index: 1897534 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.6635. Min Act: -0.1700

Data Index: 853456 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.6564. Min Act: -0.1700

Data Index: 5764618 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.6408. Min Act: -0.1700

Data Index: 8385129 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.6352. Min Act: -0.1700

Data Index: 7029384 (Open Web Text)

Max Activating Token Index: 714

Text #19

Max Range: 4.0633. Min Range: -4.0633

Max Act: 3.6294. Min Act: -0.1700

Data Index: 1711079 (Open Web Text)

Max Activating Token Index: 24