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

Dataset: Open Web Text

Neuron 1389 in Layer 2

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: 1.8768. Min Range: -1.8768

Max Act: 1.8768. Min Act: -0.1700

Data Index: 2695757 (Open Web Text)

Max Activating Token Index: 590

Text #1

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8647. Min Act: -0.1700

Data Index: 2197199 (Open Web Text)

Max Activating Token Index: 743

Text #2

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8464. Min Act: -0.1699

Data Index: 1844883 (Open Web Text)

Max Activating Token Index: 41

Text #3

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8234. Min Act: -0.1700

Data Index: 4590641 (Open Web Text)

Max Activating Token Index: 231

Text #4

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8249. Min Act: -0.1700

Data Index: 6070859 (Open Web Text)

Max Activating Token Index: 310

Text #5

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8192. Min Act: -0.1700

Data Index: 7232586 (Open Web Text)

Max Activating Token Index: 96

Text #6

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8102. Min Act: -0.1700

Data Index: 3279844 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8109. Min Act: -0.1700

Data Index: 4003516 (Open Web Text)

Max Activating Token Index: 309

Text #8

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8114. Min Act: -0.1700

Data Index: 7568281 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8111. Min Act: -0.1700

Data Index: 1789002 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8096. Min Act: -0.1700

Data Index: 2569075 (Open Web Text)

Max Activating Token Index: 181

Text #11

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8012. Min Act: -0.1700

Data Index: 5016901 (Open Web Text)

Max Activating Token Index: 902

Text #12

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.7839. Min Act: -0.1700

Data Index: 2419729 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.7967. Min Act: -0.1700

Data Index: 2840563 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.8056. Min Act: -0.1700

Data Index: 5313759 (Open Web Text)

Max Activating Token Index: 207

Text #15

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.7914. Min Act: -0.1700

Data Index: 864026 (Open Web Text)

Max Activating Token Index: 147

Text #16

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.7984. Min Act: -0.1700

Data Index: 6910880 (Open Web Text)

Max Activating Token Index: 189

Text #17

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.7829. Min Act: -0.1700

Data Index: 1698535 (Open Web Text)

Max Activating Token Index: 85

Text #18

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.7721. Min Act: -0.1700

Data Index: 3764457 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 1.8768. Min Range: -1.8768

Max Act: 1.7724. Min Act: -0.1700

Data Index: 7283510 (Open Web Text)

Max Activating Token Index: 378