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

Dataset: Open Web Text

Neuron 1900 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: 3.8452. Min Range: -3.8452

Max Act: 3.8452. Min Act: -0.1700

Data Index: 1886111 (Open Web Text)

Max Activating Token Index: 746

Text #1

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.7608. Min Act: -0.1700

Data Index: 8274804 (Open Web Text)

Max Activating Token Index: 529

Text #2

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.7932. Min Act: -0.1700

Data Index: 2779492 (Open Web Text)

Max Activating Token Index: 269

Text #3

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.7619. Min Act: -0.1700

Data Index: 7682583 (Open Web Text)

Max Activating Token Index: 105

Text #4

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.6535. Min Act: -0.1700

Data Index: 5729986 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.6030. Min Act: -0.1700

Data Index: 277466 (Open Web Text)

Max Activating Token Index: 509

Text #6

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.6302. Min Act: -0.1700

Data Index: 5902755 (Open Web Text)

Max Activating Token Index: 473

Text #7

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5917. Min Act: -0.1700

Data Index: 4340810 (Open Web Text)

Max Activating Token Index: 569

Text #8

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5682. Min Act: -0.1700

Data Index: 7829110 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5673. Min Act: -0.1700

Data Index: 5866662 (Open Web Text)

Max Activating Token Index: 316

Text #10

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5647. Min Act: -0.1700

Data Index: 2012542 (Open Web Text)

Max Activating Token Index: 263

Text #11

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5503. Min Act: -0.1700

Data Index: 2400154 (Open Web Text)

Max Activating Token Index: 599

Text #12

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5560. Min Act: -0.1700

Data Index: 1070789 (Open Web Text)

Max Activating Token Index: 887

Text #13

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5177. Min Act: -0.1700

Data Index: 4398510 (Open Web Text)

Max Activating Token Index: 621

Text #14

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5080. Min Act: -0.1700

Data Index: 6516539 (Open Web Text)

Max Activating Token Index: 350

Text #15

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5129. Min Act: -0.1700

Data Index: 1852407 (Open Web Text)

Max Activating Token Index: 543

Text #16

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5122. Min Act: -0.1700

Data Index: 1604008 (Open Web Text)

Max Activating Token Index: 828

Text #17

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5072. Min Act: -0.1700

Data Index: 8270032 (Open Web Text)

Max Activating Token Index: 463

Text #18

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5184. Min Act: -0.1700

Data Index: 4920466 (Open Web Text)

Max Activating Token Index: 896

Text #19

Max Range: 3.8452. Min Range: -3.8452

Max Act: 3.5278. Min Act: -0.1700

Data Index: 2745344 (Open Web Text)

Max Activating Token Index: 708