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

Dataset: Open Web Text

Neuron 2396 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: 1.8530. Min Range: -1.8530

Max Act: 1.8530. Min Act: -0.1700

Data Index: 2226549 (Open Web Text)

Max Activating Token Index: 1013

Text #1

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.8051. Min Act: -0.1700

Data Index: 1600530 (Open Web Text)

Max Activating Token Index: 1013

Text #2

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7867. Min Act: -0.1700

Data Index: 621669 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7734. Min Act: -0.1700

Data Index: 7280099 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7428. Min Act: -0.1700

Data Index: 4076969 (Open Web Text)

Max Activating Token Index: 621

Text #5

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7386. Min Act: -0.1700

Data Index: 621680 (Open Web Text)

Max Activating Token Index: 1007

Text #6

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7392. Min Act: -0.1700

Data Index: 1600531 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7202. Min Act: -0.1700

Data Index: 621667 (Open Web Text)

Max Activating Token Index: 918

Text #8

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.7121. Min Act: -0.1700

Data Index: 1600529 (Open Web Text)

Max Activating Token Index: 1014

Text #9

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.6435. Min Act: -0.1700

Data Index: 3485495 (Open Web Text)

Max Activating Token Index: 1003

Text #10

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.6490. Min Act: -0.1700

Data Index: 621674 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.6420. Min Act: -0.1700

Data Index: 7542419 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.6323. Min Act: -0.1700

Data Index: 621666 (Open Web Text)

Max Activating Token Index: 1020

Text #13

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.5901. Min Act: -0.1700

Data Index: 2949108 (Open Web Text)

Max Activating Token Index: 1014

Text #14

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.6046. Min Act: -0.1700

Data Index: 621679 (Open Web Text)

Max Activating Token Index: 1013

Text #15

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.5944. Min Act: -0.1700

Data Index: 680090 (Open Web Text)

Max Activating Token Index: 1013

Text #16

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.5877. Min Act: -0.1700

Data Index: 8438883 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.5896. Min Act: -0.1700

Data Index: 7096882 (Open Web Text)

Max Activating Token Index: 963

Text #18

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.5838. Min Act: -0.1700

Data Index: 621670 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 1.8530. Min Range: -1.8530

Max Act: 1.5834. Min Act: -0.1700

Data Index: 1676950 (Open Web Text)

Max Activating Token Index: 982