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

Dataset: Open Web Text

Neuron 1417 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: 5.9730. Min Range: -5.9730

Max Act: 5.9730. Min Act: -0.1700

Data Index: 2820797 (Open Web Text)

Max Activating Token Index: 950

Text #1

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.9536. Min Act: -0.1700

Data Index: 2008350 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8705. Min Act: -0.1700

Data Index: 2762739 (Open Web Text)

Max Activating Token Index: 283

Text #3

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8685. Min Act: -0.1700

Data Index: 3949310 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8989. Min Act: -0.1700

Data Index: 5457387 (Open Web Text)

Max Activating Token Index: 551

Text #5

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8635. Min Act: -0.1700

Data Index: 5492324 (Open Web Text)

Max Activating Token Index: 702

Text #6

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8480. Min Act: -0.1700

Data Index: 5295639 (Open Web Text)

Max Activating Token Index: 401

Text #7

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8332. Min Act: -0.1700

Data Index: 1265063 (Open Web Text)

Max Activating Token Index: 269

Text #8

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8178. Min Act: -0.1700

Data Index: 8538560 (Open Web Text)

Max Activating Token Index: 803

Text #9

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8429. Min Act: -0.1700

Data Index: 8401506 (Open Web Text)

Max Activating Token Index: 867

Text #10

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8570. Min Act: -0.1700

Data Index: 670668 (Open Web Text)

Max Activating Token Index: 828

Text #11

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8374. Min Act: -0.1700

Data Index: 8326429 (Open Web Text)

Max Activating Token Index: 261

Text #12

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.8195. Min Act: -0.1700

Data Index: 7645034 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.7544. Min Act: -0.1700

Data Index: 4042514 (Open Web Text)

Max Activating Token Index: 700

Text #14

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.7527. Min Act: -0.1700

Data Index: 526350 (Open Web Text)

Max Activating Token Index: 450

Text #15

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.7038. Min Act: -0.1700

Data Index: 2318425 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.7177. Min Act: -0.1700

Data Index: 2729088 (Open Web Text)

Max Activating Token Index: 706

Text #17

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.6907. Min Act: -0.1700

Data Index: 5368898 (Open Web Text)

Max Activating Token Index: 528

Text #18

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.7292. Min Act: -0.1700

Data Index: 3387001 (Open Web Text)

Max Activating Token Index: 862

Text #19

Max Range: 5.9730. Min Range: -5.9730

Max Act: 5.7269. Min Act: -0.1700

Data Index: 2800196 (Open Web Text)

Max Activating Token Index: 499