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

Dataset: Open Web Text

Neuron 2446 in Layer 1

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: 1.2619. Min Range: -1.2619

Max Act: 1.2619. Min Act: -0.1698

Data Index: 4415228 (Open Web Text)

Max Activating Token Index: 504

Text #1

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2440. Min Act: -0.1585

Data Index: 6923993 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2476. Min Act: -0.1700

Data Index: 8464863 (Open Web Text)

Max Activating Token Index: 943

Text #3

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2356. Min Act: -0.1699

Data Index: 5693888 (Open Web Text)

Max Activating Token Index: 523

Text #4

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2303. Min Act: -0.1699

Data Index: 5729094 (Open Web Text)

Max Activating Token Index: 161

Text #5

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2176. Min Act: -0.1700

Data Index: 6967946 (Open Web Text)

Max Activating Token Index: 748

Text #6

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2142. Min Act: -0.1700

Data Index: 6722830 (Open Web Text)

Max Activating Token Index: 505

Text #7

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2085. Min Act: -0.1700

Data Index: 6967949 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2010. Min Act: -0.1672

Data Index: 881048 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1974. Min Act: -0.1700

Data Index: 7200094 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1921. Min Act: -0.1700

Data Index: 6967945 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1923. Min Act: -0.1700

Data Index: 7736823 (Open Web Text)

Max Activating Token Index: 935

Text #12

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1814. Min Act: -0.1700

Data Index: 6967944 (Open Web Text)

Max Activating Token Index: 1008

Text #13

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1884. Min Act: -0.1699

Data Index: 4801439 (Open Web Text)

Max Activating Token Index: 900

Text #14

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1822. Min Act: -0.1700

Data Index: 432535 (Open Web Text)

Max Activating Token Index: 189

Text #15

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1901. Min Act: -0.1700

Data Index: 717325 (Open Web Text)

Max Activating Token Index: 68

Text #16

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1848. Min Act: -0.1700

Data Index: 3787218 (Open Web Text)

Max Activating Token Index: 723

Text #17

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1822. Min Act: -0.1700

Data Index: 4438057 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1861. Min Act: -0.1675

Data Index: 3500659 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1753. Min Act: -0.1700

Data Index: 6404643 (Open Web Text)

Max Activating Token Index: 60