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

Dataset: Open Web Text

Neuron 450 in Layer 3

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: 5.0975. Min Range: -5.0975

Max Act: 5.0975. Min Act: -0.1700

Data Index: 5480323 (Open Web Text)

Max Activating Token Index: 434

Text #1

Max Range: 5.0975. Min Range: -5.0975

Max Act: 5.0564. Min Act: -0.1700

Data Index: 342724 (Open Web Text)

Max Activating Token Index: 711

Text #2

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9954. Min Act: -0.1700

Data Index: 4791124 (Open Web Text)

Max Activating Token Index: 1003

Text #3

Max Range: 5.0975. Min Range: -5.0975

Max Act: 5.0298. Min Act: -0.1700

Data Index: 262146 (Open Web Text)

Max Activating Token Index: 471

Text #4

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9350. Min Act: -0.1700

Data Index: 8807616 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9591. Min Act: -0.1700

Data Index: 2462989 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9505. Min Act: -0.1700

Data Index: 4000782 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 5.0975. Min Range: -5.0975

Max Act: 5.0079. Min Act: -0.1700

Data Index: 7329519 (Open Web Text)

Max Activating Token Index: 104

Text #8

Max Range: 5.0975. Min Range: -5.0975

Max Act: 5.0259. Min Act: -0.1700

Data Index: 6992139 (Open Web Text)

Max Activating Token Index: 350

Text #9

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9743. Min Act: -0.1700

Data Index: 5193489 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9948. Min Act: -0.1700

Data Index: 1551543 (Open Web Text)

Max Activating Token Index: 688

Text #11

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9485. Min Act: -0.1700

Data Index: 8278701 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9980. Min Act: -0.1700

Data Index: 6187943 (Open Web Text)

Max Activating Token Index: 685

Text #13

Max Range: 5.0975. Min Range: -5.0975

Max Act: 5.0178. Min Act: -0.1700

Data Index: 3387532 (Open Web Text)

Max Activating Token Index: 31

Text #14

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9717. Min Act: -0.1700

Data Index: 7094291 (Open Web Text)

Max Activating Token Index: 458

Text #15

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9018. Min Act: -0.1700

Data Index: 8303240 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9632. Min Act: -0.1700

Data Index: 1330236 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 5.0975. Min Range: -5.0975

Max Act: 5.0033. Min Act: -0.1700

Data Index: 8038277 (Open Web Text)

Max Activating Token Index: 636

Text #18

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.8967. Min Act: -0.1700

Data Index: 920559 (Open Web Text)

Max Activating Token Index: 534

Text #19

Max Range: 5.0975. Min Range: -5.0975

Max Act: 4.9110. Min Act: -0.1700

Data Index: 1627368 (Open Web Text)

Max Activating Token Index: 531