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

Dataset: Open Web Text

Neuron 35 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: 2.7952. Min Range: -2.7952

Max Act: 2.7952. Min Act: -0.1700

Data Index: 1818169 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7807. Min Act: -0.1700

Data Index: 4089664 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7486. Min Act: -0.1700

Data Index: 7124698 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7445. Min Act: -0.1700

Data Index: 3998454 (Open Web Text)

Max Activating Token Index: 249

Text #4

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7331. Min Act: -0.1700

Data Index: 116782 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7394. Min Act: -0.1700

Data Index: 7536930 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7216. Min Act: -0.1700

Data Index: 8548268 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7168. Min Act: -0.1700

Data Index: 5325098 (Open Web Text)

Max Activating Token Index: 801

Text #8

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7169. Min Act: -0.1700

Data Index: 729218 (Open Web Text)

Max Activating Token Index: 941

Text #9

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7255. Min Act: -0.1700

Data Index: 3894439 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7032. Min Act: -0.1700

Data Index: 7711902 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.6977. Min Act: -0.1700

Data Index: 45717 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7025. Min Act: -0.1700

Data Index: 8744583 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7129. Min Act: -0.1700

Data Index: 1900761 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.7000. Min Act: -0.1700

Data Index: 5248639 (Open Web Text)

Max Activating Token Index: 39

Text #15

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.6961. Min Act: -0.1700

Data Index: 61346 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.6879. Min Act: -0.1700

Data Index: 5406571 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.6967. Min Act: -0.1700

Data Index: 5648415 (Open Web Text)

Max Activating Token Index: 882

Text #18

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.6878. Min Act: -0.1700

Data Index: 1354878 (Open Web Text)

Max Activating Token Index: 209

Text #19

Max Range: 2.7952. Min Range: -2.7952

Max Act: 2.6969. Min Act: -0.1700

Data Index: 6777588 (Open Web Text)

Max Activating Token Index: 15