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

Dataset: Open Web Text

Neuron 518 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: 2.4083. Min Range: -2.4083

Max Act: 2.4083. Min Act: -0.1700

Data Index: 5243589 (Open Web Text)

Max Activating Token Index: 90

Text #1

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3476. Min Act: -0.1700

Data Index: 3196050 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3399. Min Act: -0.1700

Data Index: 3500460 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3491. Min Act: -0.1700

Data Index: 6487629 (Open Web Text)

Max Activating Token Index: 720

Text #4

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3399. Min Act: -0.1700

Data Index: 5609448 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3532. Min Act: -0.1700

Data Index: 6273909 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3285. Min Act: -0.1700

Data Index: 7470129 (Open Web Text)

Max Activating Token Index: 151

Text #7

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3380. Min Act: -0.1700

Data Index: 6915486 (Open Web Text)

Max Activating Token Index: 1005

Text #8

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3214. Min Act: -0.1700

Data Index: 8131542 (Open Web Text)

Max Activating Token Index: 521

Text #9

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3187. Min Act: -0.1700

Data Index: 2106968 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3110. Min Act: -0.1700

Data Index: 445918 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3214. Min Act: -0.1700

Data Index: 161730 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3017. Min Act: -0.1700

Data Index: 102760 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.2562. Min Act: -0.1700

Data Index: 6251814 (Open Web Text)

Max Activating Token Index: 821

Text #14

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.2986. Min Act: -0.1700

Data Index: 8438203 (Open Web Text)

Max Activating Token Index: 431

Text #15

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.3106. Min Act: -0.1700

Data Index: 3856900 (Open Web Text)

Max Activating Token Index: 273

Text #16

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.2755. Min Act: -0.1700

Data Index: 6479626 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.2779. Min Act: -0.1700

Data Index: 6441792 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.2899. Min Act: -0.1700

Data Index: 3399857 (Open Web Text)

Max Activating Token Index: 410

Text #19

Max Range: 2.4083. Min Range: -2.4083

Max Act: 2.2893. Min Act: -0.1700

Data Index: 6788365 (Open Web Text)

Max Activating Token Index: 6