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

Dataset: Open Web Text

Neuron 49 in Layer 1

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: 1.9894. Min Range: -1.9894

Max Act: 1.9894. Min Act: -0.1700

Data Index: 6893159 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9529. Min Act: -0.1700

Data Index: 6846783 (Open Web Text)

Max Activating Token Index: 43

Text #2

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8866. Min Act: -0.1700

Data Index: 510567 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8979. Min Act: -0.1700

Data Index: 6902342 (Open Web Text)

Max Activating Token Index: 242

Text #4

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8826. Min Act: -0.1700

Data Index: 369017 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8840. Min Act: -0.1700

Data Index: 3502504 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8849. Min Act: -0.1700

Data Index: 1156980 (Open Web Text)

Max Activating Token Index: 321

Text #7

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8941. Min Act: -0.1700

Data Index: 138485 (Open Web Text)

Max Activating Token Index: 381

Text #8

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8635. Min Act: -0.1700

Data Index: 2341744 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8566. Min Act: -0.1700

Data Index: 6423542 (Open Web Text)

Max Activating Token Index: 43

Text #10

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8695. Min Act: -0.1700

Data Index: 8742399 (Open Web Text)

Max Activating Token Index: 48

Text #11

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8789. Min Act: -0.1700

Data Index: 2144147 (Open Web Text)

Max Activating Token Index: 846

Text #12

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8515. Min Act: -0.1700

Data Index: 4176939 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8564. Min Act: -0.1700

Data Index: 3887401 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8541. Min Act: -0.1700

Data Index: 8548579 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8572. Min Act: -0.1700

Data Index: 540639 (Open Web Text)

Max Activating Token Index: 655

Text #16

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8564. Min Act: -0.1700

Data Index: 5571305 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8530. Min Act: -0.1700

Data Index: 8040819 (Open Web Text)

Max Activating Token Index: 339

Text #18

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8425. Min Act: -0.1700

Data Index: 6903457 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8564. Min Act: -0.1700

Data Index: 6853521 (Open Web Text)

Max Activating Token Index: 5