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

Dataset: Open Web Text

Neuron 218 in Layer 3

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: 5.0155. Min Range: -5.0155

Max Act: 5.0155. Min Act: -0.1700

Data Index: 6192170 (Open Web Text)

Max Activating Token Index: 581

Text #1

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.9007. Min Act: -0.1700

Data Index: 2385376 (Open Web Text)

Max Activating Token Index: 336

Text #2

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.8699. Min Act: -0.1700

Data Index: 4027002 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.8795. Min Act: -0.1700

Data Index: 4473083 (Open Web Text)

Max Activating Token Index: 113

Text #4

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.8707. Min Act: -0.1700

Data Index: 4165464 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.8347. Min Act: -0.1700

Data Index: 7984174 (Open Web Text)

Max Activating Token Index: 243

Text #6

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.8356. Min Act: -0.1700

Data Index: 5273736 (Open Web Text)

Max Activating Token Index: 521

Text #7

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.8207. Min Act: -0.1700

Data Index: 6908690 (Open Web Text)

Max Activating Token Index: 316

Text #8

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.8067. Min Act: -0.1700

Data Index: 7412334 (Open Web Text)

Max Activating Token Index: 625

Text #9

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7932. Min Act: -0.1700

Data Index: 1078789 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7691. Min Act: -0.1700

Data Index: 4919037 (Open Web Text)

Max Activating Token Index: 385

Text #11

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7623. Min Act: -0.1700

Data Index: 223537 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7747. Min Act: -0.1700

Data Index: 607787 (Open Web Text)

Max Activating Token Index: 140

Text #13

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7528. Min Act: -0.1700

Data Index: 4414568 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7866. Min Act: -0.1700

Data Index: 7535786 (Open Web Text)

Max Activating Token Index: 63

Text #15

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7534. Min Act: -0.1700

Data Index: 7974626 (Open Web Text)

Max Activating Token Index: 554

Text #16

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7730. Min Act: -0.1700

Data Index: 3276262 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7482. Min Act: -0.1700

Data Index: 6140701 (Open Web Text)

Max Activating Token Index: 533

Text #18

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.8016. Min Act: -0.1700

Data Index: 8556500 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 5.0155. Min Range: -5.0155

Max Act: 4.7239. Min Act: -0.1700

Data Index: 3008691 (Open Web Text)

Max Activating Token Index: 28