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

Dataset: Open Web Text

Neuron 582 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: 3.9530. Min Range: -3.9530

Max Act: 3.9530. Min Act: -0.1700

Data Index: 5839696 (Open Web Text)

Max Activating Token Index: 474

Text #1

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.9129. Min Act: -0.1700

Data Index: 24351 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.8696. Min Act: -0.1700

Data Index: 3960118 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.8324. Min Act: -0.1700

Data Index: 5860482 (Open Web Text)

Max Activating Token Index: 215

Text #4

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.8128. Min Act: -0.1700

Data Index: 1731766 (Open Web Text)

Max Activating Token Index: 157

Text #5

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.8212. Min Act: -0.1700

Data Index: 3407137 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.8180. Min Act: -0.1700

Data Index: 4308555 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.8029. Min Act: -0.1700

Data Index: 4628315 (Open Web Text)

Max Activating Token Index: 193

Text #8

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.8036. Min Act: -0.1700

Data Index: 4767385 (Open Web Text)

Max Activating Token Index: 603

Text #9

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.8001. Min Act: -0.1700

Data Index: 2456763 (Open Web Text)

Max Activating Token Index: 551

Text #10

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7525. Min Act: -0.1700

Data Index: 3905849 (Open Web Text)

Max Activating Token Index: 414

Text #11

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7856. Min Act: -0.1700

Data Index: 1391172 (Open Web Text)

Max Activating Token Index: 285

Text #12

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7809. Min Act: -0.1700

Data Index: 4907292 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7798. Min Act: -0.1700

Data Index: 2448599 (Open Web Text)

Max Activating Token Index: 973

Text #14

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7437. Min Act: -0.1700

Data Index: 6681854 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7404. Min Act: -0.1700

Data Index: 6442119 (Open Web Text)

Max Activating Token Index: 659

Text #16

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7482. Min Act: -0.1700

Data Index: 5328742 (Open Web Text)

Max Activating Token Index: 511

Text #17

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7609. Min Act: -0.1700

Data Index: 3711731 (Open Web Text)

Max Activating Token Index: 296

Text #18

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7360. Min Act: -0.1700

Data Index: 3125832 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 3.9530. Min Range: -3.9530

Max Act: 3.7557. Min Act: -0.1700

Data Index: 3092938 (Open Web Text)

Max Activating Token Index: 595