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

Dataset: Open Web Text

Neuron 870 in Layer 5

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: 7.0767. Min Range: -7.0767

Max Act: 7.0767. Min Act: -0.1700

Data Index: 1900368 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 7.0767. Min Range: -7.0767

Max Act: 7.0064. Min Act: -0.1700

Data Index: 7381593 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.9805. Min Act: -0.1700

Data Index: 2087496 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.9898. Min Act: -0.1700

Data Index: 8657002 (Open Web Text)

Max Activating Token Index: 111

Text #4

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.9605. Min Act: -0.1700

Data Index: 3985467 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.9336. Min Act: -0.1700

Data Index: 2235000 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.9186. Min Act: -0.1700

Data Index: 4068887 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8922. Min Act: -0.1700

Data Index: 7685298 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8879. Min Act: -0.1700

Data Index: 1067958 (Open Web Text)

Max Activating Token Index: 106

Text #9

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8853. Min Act: -0.1700

Data Index: 2927610 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8175. Min Act: -0.1700

Data Index: 3612186 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8891. Min Act: -0.1700

Data Index: 4245674 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8694. Min Act: -0.1700

Data Index: 4992873 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8492. Min Act: -0.1700

Data Index: 8483577 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8431. Min Act: -0.1700

Data Index: 4206307 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8022. Min Act: -0.1700

Data Index: 4073056 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8269. Min Act: -0.1700

Data Index: 1730165 (Open Web Text)

Max Activating Token Index: 975

Text #17

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.7901. Min Act: -0.1700

Data Index: 1662572 (Open Web Text)

Max Activating Token Index: 306

Text #18

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8473. Min Act: -0.1700

Data Index: 1614965 (Open Web Text)

Max Activating Token Index: 407

Text #19

Max Range: 7.0767. Min Range: -7.0767

Max Act: 6.8116. Min Act: -0.1700

Data Index: 4232791 (Open Web Text)

Max Activating Token Index: 922