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

Dataset: Open Web Text

Neuron 2093 in Layer 4

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: 3.5259. Min Range: -3.5259

Max Act: 3.5259. Min Act: -0.1700

Data Index: 2549037 (Open Web Text)

Max Activating Token Index: 357

Text #1

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4613. Min Act: -0.1700

Data Index: 7573257 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4764. Min Act: -0.1700

Data Index: 273376 (Open Web Text)

Max Activating Token Index: 463

Text #3

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4602. Min Act: -0.1700

Data Index: 2108379 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4418. Min Act: -0.1700

Data Index: 7452391 (Open Web Text)

Max Activating Token Index: 591

Text #5

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4147. Min Act: -0.1700

Data Index: 7482337 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3939. Min Act: -0.1700

Data Index: 5785648 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3735. Min Act: -0.1700

Data Index: 7987288 (Open Web Text)

Max Activating Token Index: 157

Text #8

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4033. Min Act: -0.1700

Data Index: 5385115 (Open Web Text)

Max Activating Token Index: 389

Text #9

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3907. Min Act: -0.1700

Data Index: 464779 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3771. Min Act: -0.1700

Data Index: 734792 (Open Web Text)

Max Activating Token Index: 729

Text #11

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3610. Min Act: -0.1700

Data Index: 1480440 (Open Web Text)

Max Activating Token Index: 384

Text #12

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3837. Min Act: -0.1700

Data Index: 2825552 (Open Web Text)

Max Activating Token Index: 199

Text #13

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3957. Min Act: -0.1700

Data Index: 4110130 (Open Web Text)

Max Activating Token Index: 710

Text #14

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3981. Min Act: -0.1700

Data Index: 4151877 (Open Web Text)

Max Activating Token Index: 558

Text #15

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3291. Min Act: -0.1700

Data Index: 2620492 (Open Web Text)

Max Activating Token Index: 694

Text #16

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3504. Min Act: -0.1700

Data Index: 5049160 (Open Web Text)

Max Activating Token Index: 125

Text #17

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3641. Min Act: -0.1700

Data Index: 3102971 (Open Web Text)

Max Activating Token Index: 995

Text #18

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3352. Min Act: -0.1700

Data Index: 566241 (Open Web Text)

Max Activating Token Index: 495

Text #19

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3284. Min Act: -0.1700

Data Index: 1023445 (Open Web Text)

Max Activating Token Index: 689