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

Dataset: Open Web Text

Neuron 348 in Layer 2

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: 3.2249. Min Range: -3.2249

Max Act: 3.2249. Min Act: -0.1700

Data Index: 7043522 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.2181. Min Act: -0.1700

Data Index: 1543996 (Open Web Text)

Max Activating Token Index: 738

Text #2

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.1880. Min Act: -0.1700

Data Index: 8054843 (Open Web Text)

Max Activating Token Index: 222

Text #3

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.1533. Min Act: -0.1700

Data Index: 6621112 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.1179. Min Act: -0.1700

Data Index: 6451872 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0803. Min Act: -0.1700

Data Index: 7008739 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0775. Min Act: -0.1700

Data Index: 1832445 (Open Web Text)

Max Activating Token Index: 783

Text #7

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0702. Min Act: -0.1700

Data Index: 244536 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0734. Min Act: -0.1700

Data Index: 3545422 (Open Web Text)

Max Activating Token Index: 126

Text #9

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0717. Min Act: -0.1700

Data Index: 3700786 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0517. Min Act: -0.1700

Data Index: 1796123 (Open Web Text)

Max Activating Token Index: 58

Text #11

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0795. Min Act: -0.1700

Data Index: 7843117 (Open Web Text)

Max Activating Token Index: 631

Text #12

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0424. Min Act: -0.1700

Data Index: 6288154 (Open Web Text)

Max Activating Token Index: 725

Text #13

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0607. Min Act: -0.1700

Data Index: 7008738 (Open Web Text)

Max Activating Token Index: 960

Text #14

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0453. Min Act: -0.1700

Data Index: 662260 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0341. Min Act: -0.1700

Data Index: 8506705 (Open Web Text)

Max Activating Token Index: 626

Text #16

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0309. Min Act: -0.1700

Data Index: 2830089 (Open Web Text)

Max Activating Token Index: 515

Text #17

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0029. Min Act: -0.1700

Data Index: 4646640 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 3.2249. Min Range: -3.2249

Max Act: 3.0072. Min Act: -0.1700

Data Index: 2437152 (Open Web Text)

Max Activating Token Index: 134

Text #19

Max Range: 3.2249. Min Range: -3.2249

Max Act: 2.9827. Min Act: -0.1700

Data Index: 7666802 (Open Web Text)

Max Activating Token Index: 596