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

Dataset: Open Web Text

Neuron 557 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: 3.2691. Min Range: -3.2691

Max Act: 3.2691. Min Act: -0.1700

Data Index: 5142053 (Open Web Text)

Max Activating Token Index: 290

Text #1

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.2071. Min Act: -0.1700

Data Index: 8378717 (Open Web Text)

Max Activating Token Index: 459

Text #2

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1399. Min Act: -0.1700

Data Index: 1030904 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1065. Min Act: -0.1700

Data Index: 2737890 (Open Web Text)

Max Activating Token Index: 200

Text #4

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1051. Min Act: -0.1700

Data Index: 7510961 (Open Web Text)

Max Activating Token Index: 773

Text #5

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.1216. Min Act: -0.1700

Data Index: 3153391 (Open Web Text)

Max Activating Token Index: 885

Text #6

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0991. Min Act: -0.1700

Data Index: 3307593 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0682. Min Act: -0.1700

Data Index: 6078124 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0936. Min Act: -0.1700

Data Index: 3616481 (Open Web Text)

Max Activating Token Index: 841

Text #9

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0908. Min Act: -0.1700

Data Index: 3448320 (Open Web Text)

Max Activating Token Index: 874

Text #10

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0646. Min Act: -0.1700

Data Index: 6583670 (Open Web Text)

Max Activating Token Index: 392

Text #11

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0543. Min Act: -0.1700

Data Index: 107559 (Open Web Text)

Max Activating Token Index: 111

Text #12

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0759. Min Act: -0.1700

Data Index: 4645207 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0350. Min Act: -0.1700

Data Index: 6971320 (Open Web Text)

Max Activating Token Index: 289

Text #14

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0548. Min Act: -0.1700

Data Index: 3613244 (Open Web Text)

Max Activating Token Index: 180

Text #15

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0682. Min Act: -0.1700

Data Index: 8194043 (Open Web Text)

Max Activating Token Index: 273

Text #16

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0340. Min Act: -0.1700

Data Index: 5886960 (Open Web Text)

Max Activating Token Index: 420

Text #17

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0261. Min Act: -0.1700

Data Index: 3257814 (Open Web Text)

Max Activating Token Index: 343

Text #18

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0111. Min Act: -0.1700

Data Index: 2196963 (Open Web Text)

Max Activating Token Index: 773

Text #19

Max Range: 3.2691. Min Range: -3.2691

Max Act: 3.0407. Min Act: -0.1700

Data Index: 5571796 (Open Web Text)

Max Activating Token Index: 47