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

Dataset: Open Web Text

Neuron 439 in Layer 4

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: 3.8067. Min Range: -3.8067

Max Act: 3.8006. Min Act: -0.1700

Data Index: 4414659 (Open Web Text)

Max Activating Token Index: 500

Text #1

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7982. Min Act: -0.1700

Data Index: 330359 (Open Web Text)

Max Activating Token Index: 103

Text #2

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7522. Min Act: -0.1700

Data Index: 6780371 (Open Web Text)

Max Activating Token Index: 590

Text #3

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7779. Min Act: -0.1700

Data Index: 1429881 (Open Web Text)

Max Activating Token Index: 1003

Text #4

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7751. Min Act: -0.1700

Data Index: 2501905 (Open Web Text)

Max Activating Token Index: 375

Text #5

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.8067. Min Act: -0.1700

Data Index: 8440733 (Open Web Text)

Max Activating Token Index: 501

Text #6

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7722. Min Act: -0.1700

Data Index: 3309173 (Open Web Text)

Max Activating Token Index: 760

Text #7

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7595. Min Act: -0.1700

Data Index: 1594242 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7617. Min Act: -0.1700

Data Index: 3290357 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7206. Min Act: -0.1700

Data Index: 3928456 (Open Web Text)

Max Activating Token Index: 999

Text #10

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7175. Min Act: -0.1700

Data Index: 6944395 (Open Web Text)

Max Activating Token Index: 362

Text #11

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7313. Min Act: -0.1700

Data Index: 7342647 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7320. Min Act: -0.1700

Data Index: 5210325 (Open Web Text)

Max Activating Token Index: 272

Text #13

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7298. Min Act: -0.1700

Data Index: 5360994 (Open Web Text)

Max Activating Token Index: 745

Text #14

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6845. Min Act: -0.1700

Data Index: 3417095 (Open Web Text)

Max Activating Token Index: 791

Text #15

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6810. Min Act: -0.1700

Data Index: 162559 (Open Web Text)

Max Activating Token Index: 300

Text #16

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7057. Min Act: -0.1700

Data Index: 5341887 (Open Web Text)

Max Activating Token Index: 757

Text #17

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7071. Min Act: -0.1700

Data Index: 5320378 (Open Web Text)

Max Activating Token Index: 236

Text #18

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6736. Min Act: -0.1700

Data Index: 2695253 (Open Web Text)

Max Activating Token Index: 422

Text #19

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7191. Min Act: -0.1700

Data Index: 1712490 (Open Web Text)

Max Activating Token Index: 710