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

Dataset: Open Web Text

Neuron 2498 in Layer 6

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: 3.1433. Min Range: -3.1433

Max Act: 3.1433. Min Act: -0.1700

Data Index: 4500363 (Open Web Text)

Max Activating Token Index: 343

Text #1

Max Range: 3.1433. Min Range: -3.1433

Max Act: 3.0657. Min Act: -0.1700

Data Index: 3771869 (Open Web Text)

Max Activating Token Index: 270

Text #2

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.9478. Min Act: -0.1700

Data Index: 4448801 (Open Web Text)

Max Activating Token Index: 156

Text #3

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.9275. Min Act: -0.1700

Data Index: 4835111 (Open Web Text)

Max Activating Token Index: 661

Text #4

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.9113. Min Act: -0.1700

Data Index: 8534055 (Open Web Text)

Max Activating Token Index: 488

Text #5

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.9217. Min Act: -0.1700

Data Index: 4987500 (Open Web Text)

Max Activating Token Index: 81

Text #6

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8890. Min Act: -0.1700

Data Index: 8128068 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.9015. Min Act: -0.1700

Data Index: 3054587 (Open Web Text)

Max Activating Token Index: 546

Text #8

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8897. Min Act: -0.1700

Data Index: 6638916 (Open Web Text)

Max Activating Token Index: 767

Text #9

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.9148. Min Act: -0.1700

Data Index: 5202128 (Open Web Text)

Max Activating Token Index: 92

Text #10

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8891. Min Act: -0.1700

Data Index: 4430060 (Open Web Text)

Max Activating Token Index: 935

Text #11

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8682. Min Act: -0.1700

Data Index: 3019724 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8939. Min Act: -0.1700

Data Index: 1790877 (Open Web Text)

Max Activating Token Index: 370

Text #13

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8713. Min Act: -0.1700

Data Index: 3565265 (Open Web Text)

Max Activating Token Index: 358

Text #14

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8797. Min Act: -0.1700

Data Index: 3827905 (Open Web Text)

Max Activating Token Index: 820

Text #15

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8639. Min Act: -0.1700

Data Index: 822297 (Open Web Text)

Max Activating Token Index: 221

Text #16

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8526. Min Act: -0.1700

Data Index: 821862 (Open Web Text)

Max Activating Token Index: 757

Text #17

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8713. Min Act: -0.1700

Data Index: 4862996 (Open Web Text)

Max Activating Token Index: 603

Text #18

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8779. Min Act: -0.1700

Data Index: 4455170 (Open Web Text)

Max Activating Token Index: 135

Text #19

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.8186. Min Act: -0.1700

Data Index: 5011050 (Open Web Text)

Max Activating Token Index: 461