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

Dataset: Open Web Text

Neuron 2995 in Layer 5

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: 3.8096. Min Range: -3.8096

Max Act: 3.8096. Min Act: -0.1700

Data Index: 943960 (Open Web Text)

Max Activating Token Index: 438

Text #1

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.8019. Min Act: -0.1700

Data Index: 4720217 (Open Web Text)

Max Activating Token Index: 613

Text #2

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.7458. Min Act: -0.1700

Data Index: 5705235 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.7896. Min Act: -0.1700

Data Index: 4228016 (Open Web Text)

Max Activating Token Index: 607

Text #4

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.7196. Min Act: -0.1700

Data Index: 793127 (Open Web Text)

Max Activating Token Index: 685

Text #5

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.7191. Min Act: -0.1700

Data Index: 953524 (Open Web Text)

Max Activating Token Index: 794

Text #6

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.7066. Min Act: -0.1700

Data Index: 816560 (Open Web Text)

Max Activating Token Index: 785

Text #7

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.7572. Min Act: -0.1700

Data Index: 953525 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6931. Min Act: -0.1700

Data Index: 4051634 (Open Web Text)

Max Activating Token Index: 536

Text #9

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.7134. Min Act: -0.1700

Data Index: 7311565 (Open Web Text)

Max Activating Token Index: 252

Text #10

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.7044. Min Act: -0.1700

Data Index: 8543065 (Open Web Text)

Max Activating Token Index: 197

Text #11

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6829. Min Act: -0.1700

Data Index: 7002781 (Open Web Text)

Max Activating Token Index: 88

Text #12

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6869. Min Act: -0.1700

Data Index: 1216462 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6999. Min Act: -0.1700

Data Index: 1779512 (Open Web Text)

Max Activating Token Index: 469

Text #14

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6820. Min Act: -0.1700

Data Index: 5204486 (Open Web Text)

Max Activating Token Index: 52

Text #15

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6372. Min Act: -0.1700

Data Index: 1552622 (Open Web Text)

Max Activating Token Index: 474

Text #16

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6430. Min Act: -0.1700

Data Index: 5204485 (Open Web Text)

Max Activating Token Index: 126

Text #17

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6521. Min Act: -0.1700

Data Index: 6600837 (Open Web Text)

Max Activating Token Index: 525

Text #18

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6416. Min Act: -0.1700

Data Index: 8557056 (Open Web Text)

Max Activating Token Index: 676

Text #19

Max Range: 3.8096. Min Range: -3.8096

Max Act: 3.6153. Min Act: -0.1700

Data Index: 5502168 (Open Web Text)

Max Activating Token Index: 455