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

Dataset: Open Web Text

Neuron 2869 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: 3.8313. Min Range: -3.8313

Max Act: 3.8313. Min Act: -0.1700

Data Index: 3326 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7478. Min Act: -0.1700

Data Index: 2920115 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7049. Min Act: -0.1700

Data Index: 2275101 (Open Web Text)

Max Activating Token Index: 443

Text #3

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7033. Min Act: -0.1700

Data Index: 5324932 (Open Web Text)

Max Activating Token Index: 291

Text #4

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7244. Min Act: -0.1700

Data Index: 5559629 (Open Web Text)

Max Activating Token Index: 132

Text #5

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7074. Min Act: -0.1700

Data Index: 6510135 (Open Web Text)

Max Activating Token Index: 96

Text #6

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7242. Min Act: -0.1700

Data Index: 3707532 (Open Web Text)

Max Activating Token Index: 686

Text #7

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6907. Min Act: -0.1700

Data Index: 6965254 (Open Web Text)

Max Activating Token Index: 753

Text #8

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6743. Min Act: -0.1700

Data Index: 7661046 (Open Web Text)

Max Activating Token Index: 558

Text #9

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6580. Min Act: -0.1700

Data Index: 7492380 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6746. Min Act: -0.1700

Data Index: 920240 (Open Web Text)

Max Activating Token Index: 386

Text #11

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6607. Min Act: -0.1700

Data Index: 4221620 (Open Web Text)

Max Activating Token Index: 384

Text #12

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6509. Min Act: -0.1700

Data Index: 7146109 (Open Web Text)

Max Activating Token Index: 534

Text #13

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6514. Min Act: -0.1700

Data Index: 7221086 (Open Web Text)

Max Activating Token Index: 870

Text #14

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6636. Min Act: -0.1700

Data Index: 2047140 (Open Web Text)

Max Activating Token Index: 444

Text #15

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6530. Min Act: -0.1700

Data Index: 99285 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6483. Min Act: -0.1700

Data Index: 2998061 (Open Web Text)

Max Activating Token Index: 365

Text #17

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6460. Min Act: -0.1700

Data Index: 3608304 (Open Web Text)

Max Activating Token Index: 581

Text #18

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6602. Min Act: -0.1700

Data Index: 168668 (Open Web Text)

Max Activating Token Index: 663

Text #19

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6512. Min Act: -0.1700

Data Index: 3117567 (Open Web Text)

Max Activating Token Index: 195