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

Dataset: Open Web Text

Neuron 2012 in Layer 3

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: 3.5613. Min Range: -3.5613

Max Act: 3.5613. Min Act: -0.1700

Data Index: 7052541 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4718. Min Act: -0.1700

Data Index: 6517900 (Open Web Text)

Max Activating Token Index: 532

Text #2

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4777. Min Act: -0.1700

Data Index: 6658332 (Open Web Text)

Max Activating Token Index: 166

Text #3

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.5080. Min Act: -0.1700

Data Index: 8455716 (Open Web Text)

Max Activating Token Index: 325

Text #4

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4033. Min Act: -0.1700

Data Index: 1010528 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4026. Min Act: -0.1700

Data Index: 4506628 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4120. Min Act: -0.1700

Data Index: 8780161 (Open Web Text)

Max Activating Token Index: 949

Text #7

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3870. Min Act: -0.1700

Data Index: 588971 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4200. Min Act: -0.1700

Data Index: 861961 (Open Web Text)

Max Activating Token Index: 730

Text #9

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3781. Min Act: -0.1700

Data Index: 6752518 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4070. Min Act: -0.1700

Data Index: 1992195 (Open Web Text)

Max Activating Token Index: 305

Text #11

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4071. Min Act: -0.1700

Data Index: 3847569 (Open Web Text)

Max Activating Token Index: 402

Text #12

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3764. Min Act: -0.1700

Data Index: 3935441 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3646. Min Act: -0.1700

Data Index: 5847149 (Open Web Text)

Max Activating Token Index: 190

Text #14

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4073. Min Act: -0.1699

Data Index: 5877161 (Open Web Text)

Max Activating Token Index: 309

Text #15

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3761. Min Act: -0.1700

Data Index: 1264459 (Open Web Text)

Max Activating Token Index: 869

Text #16

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3738. Min Act: -0.1700

Data Index: 4624991 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3765. Min Act: -0.1700

Data Index: 5593239 (Open Web Text)

Max Activating Token Index: 30

Text #18

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3923. Min Act: -0.1700

Data Index: 3699972 (Open Web Text)

Max Activating Token Index: 771

Text #19

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3733. Min Act: -0.1700

Data Index: 6134015 (Open Web Text)

Max Activating Token Index: 644