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

Dataset: Open Web Text

Neuron 1651 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: 3.2788. Min Range: -3.2788

Max Act: 3.2788. Min Act: -0.1700

Data Index: 5281295 (Open Web Text)

Max Activating Token Index: 597

Text #1

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.2363. Min Act: -0.1700

Data Index: 8047429 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.2303. Min Act: -0.1700

Data Index: 1463683 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.1737. Min Act: -0.1700

Data Index: 510972 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.1559. Min Act: -0.1700

Data Index: 2678569 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.1149. Min Act: -0.1700

Data Index: 5483354 (Open Web Text)

Max Activating Token Index: 247

Text #6

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.1028. Min Act: -0.1700

Data Index: 6815997 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.1073. Min Act: -0.1700

Data Index: 7176606 (Open Web Text)

Max Activating Token Index: 149

Text #8

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.1059. Min Act: -0.1700

Data Index: 2663711 (Open Web Text)

Max Activating Token Index: 311

Text #9

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0848. Min Act: -0.1700

Data Index: 4862693 (Open Web Text)

Max Activating Token Index: 85

Text #10

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0878. Min Act: -0.1700

Data Index: 6075331 (Open Web Text)

Max Activating Token Index: 662

Text #11

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0905. Min Act: -0.1700

Data Index: 8326181 (Open Web Text)

Max Activating Token Index: 383

Text #12

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0590. Min Act: -0.1700

Data Index: 4885583 (Open Web Text)

Max Activating Token Index: 289

Text #13

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0754. Min Act: -0.1700

Data Index: 3260064 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0696. Min Act: -0.1700

Data Index: 4210420 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0625. Min Act: -0.1700

Data Index: 8693782 (Open Web Text)

Max Activating Token Index: 264

Text #16

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0531. Min Act: -0.1700

Data Index: 5054665 (Open Web Text)

Max Activating Token Index: 222

Text #17

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0677. Min Act: -0.1700

Data Index: 6763396 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0834. Min Act: -0.1700

Data Index: 6189825 (Open Web Text)

Max Activating Token Index: 451

Text #19

Max Range: 3.2788. Min Range: -3.2788

Max Act: 3.0502. Min Act: -0.1700

Data Index: 2321981 (Open Web Text)

Max Activating Token Index: 7