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

Dataset: Open Web Text

Neuron 768 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: 2.1730. Min Range: -2.1730

Max Act: 2.1708. Min Act: -0.1700

Data Index: 656202 (Open Web Text)

Max Activating Token Index: 142

Text #1

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1730. Min Act: -0.1700

Data Index: 7710411 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1488. Min Act: -0.1700

Data Index: 418129 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1502. Min Act: -0.1700

Data Index: 6327939 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1511. Min Act: -0.1700

Data Index: 1442279 (Open Web Text)

Max Activating Token Index: 74

Text #5

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1385. Min Act: -0.1700

Data Index: 6568794 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1266. Min Act: -0.1700

Data Index: 7190103 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1268. Min Act: -0.1700

Data Index: 1139543 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1333. Min Act: -0.1700

Data Index: 2440339 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1245. Min Act: -0.1700

Data Index: 5549703 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1205. Min Act: -0.1700

Data Index: 371232 (Open Web Text)

Max Activating Token Index: 36

Text #11

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1170. Min Act: -0.1700

Data Index: 6773888 (Open Web Text)

Max Activating Token Index: 20

Text #12

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0884. Min Act: -0.1700

Data Index: 6757353 (Open Web Text)

Max Activating Token Index: 934

Text #13

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.1010. Min Act: -0.1699

Data Index: 3832977 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0983. Min Act: -0.1700

Data Index: 8041058 (Open Web Text)

Max Activating Token Index: 50

Text #15

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0855. Min Act: -0.1700

Data Index: 255686 (Open Web Text)

Max Activating Token Index: 506

Text #16

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0855. Min Act: -0.1700

Data Index: 7410583 (Open Web Text)

Max Activating Token Index: 196

Text #17

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0743. Min Act: -0.1700

Data Index: 3037407 (Open Web Text)

Max Activating Token Index: 360

Text #18

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0690. Min Act: -0.1700

Data Index: 3751649 (Open Web Text)

Max Activating Token Index: 803

Text #19

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0895. Min Act: -0.1700

Data Index: 5725511 (Open Web Text)

Max Activating Token Index: 498