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

Dataset: Open Web Text

Neuron 2004 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: 3.0867. Min Range: -3.0867

Max Act: 3.0810. Min Act: -0.1700

Data Index: 3097845 (Open Web Text)

Max Activating Token Index: 28

Text #1

Max Range: 3.0867. Min Range: -3.0867

Max Act: 3.0867. Min Act: -0.1700

Data Index: 1615038 (Open Web Text)

Max Activating Token Index: 142

Text #2

Max Range: 3.0867. Min Range: -3.0867

Max Act: 3.0736. Min Act: -0.1700

Data Index: 6931024 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 3.0867. Min Range: -3.0867

Max Act: 3.0320. Min Act: -0.1700

Data Index: 1454173 (Open Web Text)

Max Activating Token Index: 160

Text #4

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9926. Min Act: -0.1700

Data Index: 3571489 (Open Web Text)

Max Activating Token Index: 876

Text #5

Max Range: 3.0867. Min Range: -3.0867

Max Act: 3.0025. Min Act: -0.1700

Data Index: 296802 (Open Web Text)

Max Activating Token Index: 738

Text #6

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9858. Min Act: -0.1700

Data Index: 981366 (Open Web Text)

Max Activating Token Index: 400

Text #7

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9757. Min Act: -0.1700

Data Index: 6212602 (Open Web Text)

Max Activating Token Index: 956

Text #8

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9585. Min Act: -0.1700

Data Index: 6414634 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9716. Min Act: -0.1700

Data Index: 702502 (Open Web Text)

Max Activating Token Index: 718

Text #10

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9511. Min Act: -0.1700

Data Index: 134318 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9528. Min Act: -0.1700

Data Index: 2651504 (Open Web Text)

Max Activating Token Index: 225

Text #12

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9583. Min Act: -0.1700

Data Index: 498629 (Open Web Text)

Max Activating Token Index: 814

Text #13

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9541. Min Act: -0.1700

Data Index: 8542104 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9256. Min Act: -0.1700

Data Index: 5234759 (Open Web Text)

Max Activating Token Index: 828

Text #15

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9397. Min Act: -0.1700

Data Index: 6842761 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9476. Min Act: -0.1700

Data Index: 6457008 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9141. Min Act: -0.1700

Data Index: 5421986 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9196. Min Act: -0.1700

Data Index: 4014733 (Open Web Text)

Max Activating Token Index: 160

Text #19

Max Range: 3.0867. Min Range: -3.0867

Max Act: 2.9067. Min Act: -0.1700

Data Index: 1480697 (Open Web Text)

Max Activating Token Index: 907