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

Dataset: Open Web Text

Neuron 1621 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: 6.1281. Min Range: -6.1281

Max Act: 6.1281. Min Act: -0.1700

Data Index: 157277 (Open Web Text)

Max Activating Token Index: 241

Text #1

Max Range: 6.1281. Min Range: -6.1281

Max Act: 6.0512. Min Act: -0.1700

Data Index: 2737912 (Open Web Text)

Max Activating Token Index: 792

Text #2

Max Range: 6.1281. Min Range: -6.1281

Max Act: 6.0418. Min Act: -0.1700

Data Index: 7653639 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 6.1281. Min Range: -6.1281

Max Act: 6.0062. Min Act: -0.1700

Data Index: 4649844 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.8643. Min Act: -0.1700

Data Index: 4540726 (Open Web Text)

Max Activating Token Index: 239

Text #5

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.7676. Min Act: -0.1700

Data Index: 7024031 (Open Web Text)

Max Activating Token Index: 937

Text #6

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.7995. Min Act: -0.1700

Data Index: 7409917 (Open Web Text)

Max Activating Token Index: 866

Text #7

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.7436. Min Act: -0.1700

Data Index: 618085 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.7625. Min Act: -0.1700

Data Index: 3312280 (Open Web Text)

Max Activating Token Index: 332

Text #9

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.6843. Min Act: -0.1700

Data Index: 1019329 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.6703. Min Act: -0.1700

Data Index: 2822310 (Open Web Text)

Max Activating Token Index: 286

Text #11

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.6493. Min Act: -0.1700

Data Index: 6742545 (Open Web Text)

Max Activating Token Index: 782

Text #12

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.6375. Min Act: -0.1700

Data Index: 6746820 (Open Web Text)

Max Activating Token Index: 308

Text #13

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.6507. Min Act: -0.1700

Data Index: 2032119 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.6403. Min Act: -0.1700

Data Index: 2234613 (Open Web Text)

Max Activating Token Index: 398

Text #15

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.6458. Min Act: -0.1700

Data Index: 114844 (Open Web Text)

Max Activating Token Index: 262

Text #16

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.6174. Min Act: -0.1700

Data Index: 3344684 (Open Web Text)

Max Activating Token Index: 835

Text #17

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.5813. Min Act: -0.1700

Data Index: 114843 (Open Web Text)

Max Activating Token Index: 55

Text #18

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.5712. Min Act: -0.1700

Data Index: 1322745 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 6.1281. Min Range: -6.1281

Max Act: 5.5950. Min Act: -0.1700

Data Index: 7248586 (Open Web Text)

Max Activating Token Index: 53