Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 1930 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.9064. Min Act: -0.1700

Data Index: 2700489 (Open Web Text)

Max Activating Token Index: 789

Text #1

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.6564. Min Act: -0.1700

Data Index: 5551135 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.6564. Min Act: -0.1700

Data Index: 5551138 (Open Web Text)

Max Activating Token Index: 185

Text #3

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.6876. Min Act: -0.1700

Data Index: 5559238 (Open Web Text)

Max Activating Token Index: 186

Text #4

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.5314. Min Act: -0.1700

Data Index: 1718783 (Open Web Text)

Max Activating Token Index: 196

Text #5

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.4689. Min Act: -0.1700

Data Index: 3982970 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.3126. Min Act: -0.1700

Data Index: 5072602 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.4064. Min Act: -0.1700

Data Index: 3475126 (Open Web Text)

Max Activating Token Index: 749

Text #8

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.1876. Min Act: -0.1700

Data Index: 2988631 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.1564. Min Act: -0.1700

Data Index: 6748099 (Open Web Text)

Max Activating Token Index: 208

Text #10

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.0939. Min Act: -0.1700

Data Index: 1241365 (Open Web Text)

Max Activating Token Index: 1005

Text #11

Max Range: 7.9064. Min Range: -7.9064

Max Act: 6.9689. Min Act: -0.1700

Data Index: 5883533 (Open Web Text)

Max Activating Token Index: 745

Text #12

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.0626. Min Act: -0.1700

Data Index: 6921153 (Open Web Text)

Max Activating Token Index: 661

Text #13

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.1251. Min Act: -0.1700

Data Index: 5715626 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.0939. Min Act: -0.1700

Data Index: 2832855 (Open Web Text)

Max Activating Token Index: 563

Text #15

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.0939. Min Act: -0.1700

Data Index: 7401476 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.0314. Min Act: -0.1700

Data Index: 6452669 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.0314. Min Act: -0.1700

Data Index: 5646036 (Open Web Text)

Max Activating Token Index: 511

Text #18

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.0314. Min Act: -0.1700

Data Index: 5983166 (Open Web Text)

Max Activating Token Index: 741

Text #19

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.0314. Min Act: -0.1700

Data Index: 5091138 (Open Web Text)

Max Activating Token Index: 426