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

Dataset: Open Web Text

Neuron 857 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: 1.6404. Min Range: -1.6404

Max Act: 1.6404. Min Act: -0.1700

Data Index: 4409367 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6238. Min Act: -0.1700

Data Index: 470411 (Open Web Text)

Max Activating Token Index: 800

Text #2

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6328. Min Act: -0.1700

Data Index: 2554657 (Open Web Text)

Max Activating Token Index: 458

Text #3

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6362. Min Act: -0.1700

Data Index: 5982356 (Open Web Text)

Max Activating Token Index: 401

Text #4

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6289. Min Act: -0.1700

Data Index: 970220 (Open Web Text)

Max Activating Token Index: 441

Text #5

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6213. Min Act: -0.1700

Data Index: 1107121 (Open Web Text)

Max Activating Token Index: 893

Text #6

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6089. Min Act: -0.1700

Data Index: 3346321 (Open Web Text)

Max Activating Token Index: 512

Text #7

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6098. Min Act: -0.1700

Data Index: 6369072 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6107. Min Act: -0.1700

Data Index: 4174821 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5996. Min Act: -0.1700

Data Index: 7998352 (Open Web Text)

Max Activating Token Index: 714

Text #10

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5946. Min Act: -0.1700

Data Index: 3178104 (Open Web Text)

Max Activating Token Index: 690

Text #11

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5976. Min Act: -0.1700

Data Index: 3778724 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5883. Min Act: -0.1700

Data Index: 5086788 (Open Web Text)

Max Activating Token Index: 127

Text #13

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5824. Min Act: -0.1700

Data Index: 2031536 (Open Web Text)

Max Activating Token Index: 651

Text #14

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5838. Min Act: -0.1700

Data Index: 8780266 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5814. Min Act: -0.1700

Data Index: 6272122 (Open Web Text)

Max Activating Token Index: 521

Text #16

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5746. Min Act: -0.1700

Data Index: 1650454 (Open Web Text)

Max Activating Token Index: 517

Text #17

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5737. Min Act: -0.1700

Data Index: 1260475 (Open Web Text)

Max Activating Token Index: 382

Text #18

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5643. Min Act: -0.1700

Data Index: 2001833 (Open Web Text)

Max Activating Token Index: 429

Text #19

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5733. Min Act: -0.1700

Data Index: 7045692 (Open Web Text)

Max Activating Token Index: 430