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

Dataset: Open Web Text

Neuron 2832 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: 3.0107. Min Range: -3.0107

Max Act: 3.0107. Min Act: -0.1700

Data Index: 6701578 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.8948. Min Act: -0.1700

Data Index: 1227053 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.8466. Min Act: -0.1700

Data Index: 2642056 (Open Web Text)

Max Activating Token Index: 272

Text #3

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.8051. Min Act: -0.1700

Data Index: 2796928 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.8178. Min Act: -0.1700

Data Index: 3258475 (Open Web Text)

Max Activating Token Index: 666

Text #5

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7964. Min Act: -0.1700

Data Index: 6478139 (Open Web Text)

Max Activating Token Index: 893

Text #6

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7947. Min Act: -0.1700

Data Index: 7902512 (Open Web Text)

Max Activating Token Index: 809

Text #7

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7768. Min Act: -0.1700

Data Index: 5295492 (Open Web Text)

Max Activating Token Index: 564

Text #8

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.8138. Min Act: -0.1700

Data Index: 7162906 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7782. Min Act: -0.1700

Data Index: 7120054 (Open Web Text)

Max Activating Token Index: 65

Text #10

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.8095. Min Act: -0.1700

Data Index: 6132890 (Open Web Text)

Max Activating Token Index: 664

Text #11

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7669. Min Act: -0.1700

Data Index: 3562574 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7727. Min Act: -0.1700

Data Index: 3971202 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7722. Min Act: -0.1700

Data Index: 449603 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7293. Min Act: -0.1700

Data Index: 5951373 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7310. Min Act: -0.1700

Data Index: 2156320 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7656. Min Act: -0.1700

Data Index: 7734356 (Open Web Text)

Max Activating Token Index: 134

Text #17

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7453. Min Act: -0.1700

Data Index: 6273872 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7520. Min Act: -0.1700

Data Index: 8421131 (Open Web Text)

Max Activating Token Index: 744

Text #19

Max Range: 3.0107. Min Range: -3.0107

Max Act: 2.7301. Min Act: -0.1700

Data Index: 6271142 (Open Web Text)

Max Activating Token Index: 286