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

Dataset: Open Web Text

Neuron 2587 in Layer 0

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: 6.2877. Min Range: -6.2877

Max Act: 6.2877. Min Act: -0.1700

Data Index: 8207382 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.2167. Min Act: -0.1700

Data Index: 1109239 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.2167. Min Act: -0.1700

Data Index: 843214 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1719. Min Act: -0.1700

Data Index: 4240206 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1872. Min Act: -0.1700

Data Index: 620541 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1689. Min Act: -0.1700

Data Index: 6261090 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1724. Min Act: -0.1700

Data Index: 4501203 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1741. Min Act: -0.1700

Data Index: 2083542 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1668. Min Act: -0.1700

Data Index: 2049801 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1826. Min Act: -0.1700

Data Index: 1310730 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1381. Min Act: -0.1700

Data Index: 868183 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1446. Min Act: -0.1700

Data Index: 6031880 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1388. Min Act: -0.1700

Data Index: 3152945 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1356. Min Act: -0.1700

Data Index: 7857576 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1489. Min Act: -0.1700

Data Index: 1957909 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1466. Min Act: -0.1700

Data Index: 2892934 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1465. Min Act: -0.1700

Data Index: 3698899 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.0961. Min Act: -0.1700

Data Index: 3670409 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.1130. Min Act: -0.1700

Data Index: 492960 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 6.2877. Min Range: -6.2877

Max Act: 6.0970. Min Act: -0.1700

Data Index: 3092130 (Open Web Text)

Max Activating Token Index: 7