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

Dataset: Open Web Text

Neuron 2357 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: 3.0638. Min Range: -3.0638

Max Act: 3.0638. Min Act: -0.1700

Data Index: 4673660 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0514. Min Act: -0.1700

Data Index: 4005588 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0403. Min Act: -0.1700

Data Index: 1372700 (Open Web Text)

Max Activating Token Index: 870

Text #3

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0290. Min Act: -0.1700

Data Index: 3189665 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0122. Min Act: -0.1700

Data Index: 5662470 (Open Web Text)

Max Activating Token Index: 480

Text #5

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0059. Min Act: -0.1700

Data Index: 6758701 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0051. Min Act: -0.1700

Data Index: 4669028 (Open Web Text)

Max Activating Token Index: 893

Text #7

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.9978. Min Act: -0.1700

Data Index: 4684584 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0210. Min Act: -0.1700

Data Index: 1574289 (Open Web Text)

Max Activating Token Index: 647

Text #9

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0110. Min Act: -0.1700

Data Index: 1720675 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0145. Min Act: -0.1700

Data Index: 3299882 (Open Web Text)

Max Activating Token Index: 755

Text #11

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0030. Min Act: -0.1700

Data Index: 7116237 (Open Web Text)

Max Activating Token Index: 372

Text #12

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.9883. Min Act: -0.1700

Data Index: 1129392 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.9869. Min Act: -0.1700

Data Index: 4204930 (Open Web Text)

Max Activating Token Index: 427

Text #14

Max Range: 3.0638. Min Range: -3.0638

Max Act: 3.0015. Min Act: -0.1700

Data Index: 5987474 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.9828. Min Act: -0.1700

Data Index: 71617 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.9843. Min Act: -0.1700

Data Index: 3236879 (Open Web Text)

Max Activating Token Index: 681

Text #17

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.9802. Min Act: -0.1700

Data Index: 2444568 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.9912. Min Act: -0.1700

Data Index: 3939266 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 3.0638. Min Range: -3.0638

Max Act: 2.9812. Min Act: -0.1700

Data Index: 6756174 (Open Web Text)

Max Activating Token Index: 47