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

Dataset: Open Web Text

Neuron 905 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: 5.1607. Min Range: -5.1607

Max Act: 5.1607. Min Act: -0.1700

Data Index: 5548747 (Open Web Text)

Max Activating Token Index: 650

Text #1

Max Range: 5.1607. Min Range: -5.1607

Max Act: 5.0932. Min Act: -0.1700

Data Index: 967706 (Open Web Text)

Max Activating Token Index: 983

Text #2

Max Range: 5.1607. Min Range: -5.1607

Max Act: 5.0316. Min Act: -0.1700

Data Index: 8572728 (Open Web Text)

Max Activating Token Index: 483

Text #3

Max Range: 5.1607. Min Range: -5.1607

Max Act: 5.0286. Min Act: -0.1700

Data Index: 1362619 (Open Web Text)

Max Activating Token Index: 98

Text #4

Max Range: 5.1607. Min Range: -5.1607

Max Act: 5.0085. Min Act: -0.1700

Data Index: 175500 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.9769. Min Act: -0.1700

Data Index: 3065288 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.9546. Min Act: -0.1700

Data Index: 3959081 (Open Web Text)

Max Activating Token Index: 350

Text #7

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.9338. Min Act: -0.1700

Data Index: 3550791 (Open Web Text)

Max Activating Token Index: 152

Text #8

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.9399. Min Act: -0.1700

Data Index: 4779253 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.9207. Min Act: -0.1700

Data Index: 6502026 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.9165. Min Act: -0.1700

Data Index: 5748894 (Open Web Text)

Max Activating Token Index: 149

Text #11

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.8914. Min Act: -0.1700

Data Index: 4044755 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.8854. Min Act: -0.1700

Data Index: 8419580 (Open Web Text)

Max Activating Token Index: 153

Text #13

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.8881. Min Act: -0.1700

Data Index: 1337612 (Open Web Text)

Max Activating Token Index: 657

Text #14

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.8966. Min Act: -0.1700

Data Index: 7727916 (Open Web Text)

Max Activating Token Index: 127

Text #15

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.8970. Min Act: -0.1700

Data Index: 6623178 (Open Web Text)

Max Activating Token Index: 942

Text #16

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.8939. Min Act: -0.1700

Data Index: 3948629 (Open Web Text)

Max Activating Token Index: 171

Text #17

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.8797. Min Act: -0.1700

Data Index: 3870451 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.8869. Min Act: -0.1700

Data Index: 4351323 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 5.1607. Min Range: -5.1607

Max Act: 4.8642. Min Act: -0.1700

Data Index: 487861 (Open Web Text)

Max Activating Token Index: 989