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

Dataset: Open Web Text

Neuron 2233 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: 5.0353. Min Range: -5.0353

Max Act: 5.0353. Min Act: -0.1692

Data Index: 1477595 (Open Web Text)

Max Activating Token Index: 386

Text #1

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.9841. Min Act: -0.1700

Data Index: 8072814 (Open Web Text)

Max Activating Token Index: 861

Text #2

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.9503. Min Act: -0.1700

Data Index: 6684110 (Open Web Text)

Max Activating Token Index: 818

Text #3

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.9134. Min Act: -0.1700

Data Index: 6621404 (Open Web Text)

Max Activating Token Index: 775

Text #4

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8505. Min Act: -0.1677

Data Index: 2587019 (Open Web Text)

Max Activating Token Index: 126

Text #5

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8312. Min Act: -0.1700

Data Index: 1477606 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8845. Min Act: -0.1700

Data Index: 6621405 (Open Web Text)

Max Activating Token Index: 862

Text #7

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8607. Min Act: -0.1648

Data Index: 6140838 (Open Web Text)

Max Activating Token Index: 91

Text #8

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8581. Min Act: -0.1700

Data Index: 2552662 (Open Web Text)

Max Activating Token Index: 248

Text #9

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8436. Min Act: -0.1700

Data Index: 7398764 (Open Web Text)

Max Activating Token Index: 528

Text #10

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8175. Min Act: -0.1700

Data Index: 2542940 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8439. Min Act: -0.1700

Data Index: 7398759 (Open Web Text)

Max Activating Token Index: 910

Text #12

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8402. Min Act: -0.1687

Data Index: 1477607 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8087. Min Act: -0.1700

Data Index: 2798209 (Open Web Text)

Max Activating Token Index: 118

Text #14

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8062. Min Act: -0.1663

Data Index: 2787136 (Open Web Text)

Max Activating Token Index: 174

Text #15

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.8019. Min Act: -0.1700

Data Index: 44276 (Open Web Text)

Max Activating Token Index: 113

Text #16

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.7581. Min Act: -0.1600

Data Index: 2787134 (Open Web Text)

Max Activating Token Index: 164

Text #17

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.7993. Min Act: -0.1700

Data Index: 7398772 (Open Web Text)

Max Activating Token Index: 102

Text #18

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.7917. Min Act: -0.1657

Data Index: 5709323 (Open Web Text)

Max Activating Token Index: 158

Text #19

Max Range: 5.0353. Min Range: -5.0353

Max Act: 4.7107. Min Act: -0.1700

Data Index: 44259 (Open Web Text)

Max Activating Token Index: 382