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

Dataset: Open Web Text

Neuron 160 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: 3.7713. Min Range: -3.7713

Max Act: 3.7713. Min Act: -0.1700

Data Index: 3251177 (Open Web Text)

Max Activating Token Index: 628

Text #1

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.6674. Min Act: -0.1700

Data Index: 2147615 (Open Web Text)

Max Activating Token Index: 667

Text #2

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.6485. Min Act: -0.1700

Data Index: 2095771 (Open Web Text)

Max Activating Token Index: 217

Text #3

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.6459. Min Act: -0.1700

Data Index: 796837 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.6469. Min Act: -0.1700

Data Index: 6791557 (Open Web Text)

Max Activating Token Index: 97

Text #5

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.6591. Min Act: -0.1700

Data Index: 2799058 (Open Web Text)

Max Activating Token Index: 643

Text #6

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.6421. Min Act: -0.1700

Data Index: 1849168 (Open Web Text)

Max Activating Token Index: 671

Text #7

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.6056. Min Act: -0.1700

Data Index: 6205106 (Open Web Text)

Max Activating Token Index: 380

Text #8

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.5720. Min Act: -0.1700

Data Index: 2575741 (Open Web Text)

Max Activating Token Index: 881

Text #9

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.5884. Min Act: -0.1700

Data Index: 1785305 (Open Web Text)

Max Activating Token Index: 361

Text #10

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.5555. Min Act: -0.1700

Data Index: 7568643 (Open Web Text)

Max Activating Token Index: 887

Text #11

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.6052. Min Act: -0.1700

Data Index: 3383924 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.5673. Min Act: -0.1700

Data Index: 6594436 (Open Web Text)

Max Activating Token Index: 799

Text #13

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.5410. Min Act: -0.1700

Data Index: 2114813 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.4921. Min Act: -0.1700

Data Index: 5061704 (Open Web Text)

Max Activating Token Index: 796

Text #15

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.4901. Min Act: -0.1700

Data Index: 166072 (Open Web Text)

Max Activating Token Index: 854

Text #16

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.4871. Min Act: -0.1700

Data Index: 6362495 (Open Web Text)

Max Activating Token Index: 713

Text #17

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.5053. Min Act: -0.1700

Data Index: 2008073 (Open Web Text)

Max Activating Token Index: 131

Text #18

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.5032. Min Act: -0.1700

Data Index: 5183658 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 3.7713. Min Range: -3.7713

Max Act: 3.4816. Min Act: -0.1700

Data Index: 6558120 (Open Web Text)

Max Activating Token Index: 603