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

Dataset: Open Web Text

Neuron 235 in Layer 6

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: 5.4105. Min Range: -5.4105

Max Act: 5.4105. Min Act: -0.1700

Data Index: 8218613 (Open Web Text)

Max Activating Token Index: 784

Text #1

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.4047. Min Act: -0.1700

Data Index: 2099808 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.3752. Min Act: -0.1700

Data Index: 7120014 (Open Web Text)

Max Activating Token Index: 618

Text #3

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.3519. Min Act: -0.1700

Data Index: 6922218 (Open Web Text)

Max Activating Token Index: 455

Text #4

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.3430. Min Act: -0.1700

Data Index: 282041 (Open Web Text)

Max Activating Token Index: 618

Text #5

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.3336. Min Act: -0.1700

Data Index: 456574 (Open Web Text)

Max Activating Token Index: 831

Text #6

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.2512. Min Act: -0.1700

Data Index: 5775393 (Open Web Text)

Max Activating Token Index: 902

Text #7

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.2829. Min Act: -0.1700

Data Index: 4389128 (Open Web Text)

Max Activating Token Index: 355

Text #8

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.2709. Min Act: -0.1700

Data Index: 2426274 (Open Web Text)

Max Activating Token Index: 129

Text #9

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.2253. Min Act: -0.1700

Data Index: 7104018 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.2199. Min Act: -0.1700

Data Index: 4138202 (Open Web Text)

Max Activating Token Index: 752

Text #11

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.2077. Min Act: -0.1700

Data Index: 219205 (Open Web Text)

Max Activating Token Index: 834

Text #12

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.2166. Min Act: -0.1700

Data Index: 8520466 (Open Web Text)

Max Activating Token Index: 875

Text #13

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.1858. Min Act: -0.1700

Data Index: 267763 (Open Web Text)

Max Activating Token Index: 179

Text #14

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.1881. Min Act: -0.1700

Data Index: 8231036 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.1995. Min Act: -0.1700

Data Index: 1090807 (Open Web Text)

Max Activating Token Index: 249

Text #16

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.1594. Min Act: -0.1700

Data Index: 843149 (Open Web Text)

Max Activating Token Index: 916

Text #17

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.1566. Min Act: -0.1700

Data Index: 1023425 (Open Web Text)

Max Activating Token Index: 449

Text #18

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.2051. Min Act: -0.1700

Data Index: 948784 (Open Web Text)

Max Activating Token Index: 589

Text #19

Max Range: 5.4105. Min Range: -5.4105

Max Act: 5.1678. Min Act: -0.1700

Data Index: 3010595 (Open Web Text)

Max Activating Token Index: 532