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

Dataset: Open Web Text

Neuron 2791 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: 5.7996. Min Range: -5.7996

Max Act: 5.7996. Min Act: -0.1700

Data Index: 436753 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6554. Min Act: -0.1700

Data Index: 838730 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6571. Min Act: -0.1700

Data Index: 7712287 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6603. Min Act: -0.1700

Data Index: 7693638 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6467. Min Act: -0.1700

Data Index: 8162993 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6416. Min Act: -0.1700

Data Index: 2242806 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6384. Min Act: -0.1700

Data Index: 4663275 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6073. Min Act: -0.1700

Data Index: 337842 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6279. Min Act: -0.1700

Data Index: 3886437 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6306. Min Act: -0.1700

Data Index: 8598204 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.5970. Min Act: -0.1700

Data Index: 1431471 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.6125. Min Act: -0.1700

Data Index: 6957310 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.5903. Min Act: -0.1700

Data Index: 4062144 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.5920. Min Act: -0.1700

Data Index: 5356097 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.5864. Min Act: -0.1700

Data Index: 6252867 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.5756. Min Act: -0.1700

Data Index: 5659859 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.5869. Min Act: -0.1700

Data Index: 5523276 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.5802. Min Act: -0.1700

Data Index: 2754336 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.5472. Min Act: -0.1700

Data Index: 2979282 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.7996. Min Range: -5.7996

Max Act: 5.5779. Min Act: -0.1700

Data Index: 7760796 (Open Web Text)

Max Activating Token Index: 3