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

Dataset: Open Web Text

Neuron 2820 in Layer 0

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: 1.9019. Min Range: -1.9019

Max Act: 1.9019. Min Act: -0.1693

Data Index: 2097643 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8443. Min Act: -0.1700

Data Index: 5154935 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8445. Min Act: -0.1699

Data Index: 3111819 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8465. Min Act: -0.1700

Data Index: 1766286 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8314. Min Act: -0.1672

Data Index: 1123720 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8238. Min Act: -0.1659

Data Index: 6332521 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8283. Min Act: -0.1700

Data Index: 3386524 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8277. Min Act: -0.1694

Data Index: 4370796 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8201. Min Act: -0.1684

Data Index: 780676 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8187. Min Act: -0.1700

Data Index: 2071873 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8190. Min Act: -0.1700

Data Index: 2578730 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8100. Min Act: -0.1698

Data Index: 4565278 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8109. Min Act: -0.1698

Data Index: 7835183 (Open Web Text)

Max Activating Token Index: 25

Text #13

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8091. Min Act: -0.1695

Data Index: 2638067 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8111. Min Act: -0.1697

Data Index: 4011157 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8071. Min Act: -0.1700

Data Index: 6585835 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8048. Min Act: -0.1687

Data Index: 7129309 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.7966. Min Act: -0.1700

Data Index: 7462204 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.7994. Min Act: -0.1700

Data Index: 6534672 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.8007. Min Act: -0.1700

Data Index: 5026423 (Open Web Text)

Max Activating Token Index: 8