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

Dataset: Open Web Text

Neuron 95 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: 1.6313. Min Range: -1.6313

Max Act: 1.6313. Min Act: -0.1700

Data Index: 7447404 (Open Web Text)

Max Activating Token Index: 553

Text #1

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.6012. Min Act: -0.1700

Data Index: 842012 (Open Web Text)

Max Activating Token Index: 135

Text #2

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5983. Min Act: -0.1700

Data Index: 5835025 (Open Web Text)

Max Activating Token Index: 324

Text #3

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5924. Min Act: -0.1700

Data Index: 5046031 (Open Web Text)

Max Activating Token Index: 501

Text #4

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5968. Min Act: -0.1700

Data Index: 3273346 (Open Web Text)

Max Activating Token Index: 90

Text #5

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5763. Min Act: -0.1700

Data Index: 8184055 (Open Web Text)

Max Activating Token Index: 961

Text #6

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5831. Min Act: -0.1700

Data Index: 4373332 (Open Web Text)

Max Activating Token Index: 86

Text #7

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5884. Min Act: -0.1700

Data Index: 2996185 (Open Web Text)

Max Activating Token Index: 746

Text #8

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5813. Min Act: -0.1700

Data Index: 3681094 (Open Web Text)

Max Activating Token Index: 44

Text #9

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5842. Min Act: -0.1700

Data Index: 6989418 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5782. Min Act: -0.1700

Data Index: 1825206 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5686. Min Act: -0.1700

Data Index: 5957396 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5792. Min Act: -0.1700

Data Index: 617140 (Open Web Text)

Max Activating Token Index: 683

Text #13

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5704. Min Act: -0.1700

Data Index: 6037581 (Open Web Text)

Max Activating Token Index: 716

Text #14

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5779. Min Act: -0.1700

Data Index: 2762027 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5676. Min Act: -0.1700

Data Index: 6358436 (Open Web Text)

Max Activating Token Index: 487

Text #16

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5722. Min Act: -0.1700

Data Index: 6320100 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5666. Min Act: -0.1700

Data Index: 1285783 (Open Web Text)

Max Activating Token Index: 209

Text #18

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5609. Min Act: -0.1700

Data Index: 6664652 (Open Web Text)

Max Activating Token Index: 710

Text #19

Max Range: 1.6313. Min Range: -1.6313

Max Act: 1.5660. Min Act: -0.1700

Data Index: 6312177 (Open Web Text)

Max Activating Token Index: 163