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

Dataset: Open Web Text

Neuron 2097 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: 1.8944. Min Range: -1.8944

Max Act: 1.8944. Min Act: -0.1700

Data Index: 2383726 (Open Web Text)

Max Activating Token Index: 186

Text #1

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.8720. Min Act: -0.1700

Data Index: 3931887 (Open Web Text)

Max Activating Token Index: 914

Text #2

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.8263. Min Act: -0.1700

Data Index: 6404305 (Open Web Text)

Max Activating Token Index: 860

Text #3

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.8198. Min Act: -0.1700

Data Index: 5396188 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.8116. Min Act: -0.1700

Data Index: 3035773 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7982. Min Act: -0.1700

Data Index: 4123843 (Open Web Text)

Max Activating Token Index: 48

Text #6

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7988. Min Act: -0.1700

Data Index: 7520534 (Open Web Text)

Max Activating Token Index: 534

Text #7

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7779. Min Act: -0.1700

Data Index: 1906560 (Open Web Text)

Max Activating Token Index: 341

Text #8

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7844. Min Act: -0.1700

Data Index: 3931891 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7883. Min Act: -0.1700

Data Index: 3412533 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7674. Min Act: -0.1700

Data Index: 1044463 (Open Web Text)

Max Activating Token Index: 993

Text #11

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7793. Min Act: -0.1700

Data Index: 3253172 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7755. Min Act: -0.1700

Data Index: 4924532 (Open Web Text)

Max Activating Token Index: 206

Text #13

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7726. Min Act: -0.1700

Data Index: 8407275 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7635. Min Act: -0.1700

Data Index: 5640723 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7680. Min Act: -0.1700

Data Index: 4067981 (Open Web Text)

Max Activating Token Index: 384

Text #16

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7623. Min Act: -0.1700

Data Index: 78690 (Open Web Text)

Max Activating Token Index: 45

Text #17

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7690. Min Act: -0.1700

Data Index: 6815394 (Open Web Text)

Max Activating Token Index: 59

Text #18

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7668. Min Act: -0.1700

Data Index: 6684147 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7683. Min Act: -0.1700

Data Index: 9696 (Open Web Text)

Max Activating Token Index: 189