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

Dataset: Open Web Text

Neuron 2625 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: 1.1043. Min Range: -1.1043

Max Act: 1.1043. Min Act: -0.0932

Data Index: 6891268 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0975. Min Act: -0.1113

Data Index: 361679 (Open Web Text)

Max Activating Token Index: 51

Text #2

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0995. Min Act: -0.0814

Data Index: 1509832 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.1022. Min Act: -0.0668

Data Index: 160595 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0948. Min Act: -0.1051

Data Index: 6706871 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0890. Min Act: -0.1205

Data Index: 8648595 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0893. Min Act: -0.1051

Data Index: 6949975 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0896. Min Act: -0.0794

Data Index: 4089443 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0836. Min Act: -0.1183

Data Index: 1476983 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0807. Min Act: -0.0887

Data Index: 2181248 (Open Web Text)

Max Activating Token Index: 52

Text #10

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0818. Min Act: -0.1134

Data Index: 4240589 (Open Web Text)

Max Activating Token Index: 47

Text #11

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0682. Min Act: -0.0825

Data Index: 1129333 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0719. Min Act: -0.1014

Data Index: 7613883 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0745. Min Act: -0.1128

Data Index: 2479946 (Open Web Text)

Max Activating Token Index: 41

Text #14

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0659. Min Act: -0.1085

Data Index: 8496743 (Open Web Text)

Max Activating Token Index: 58

Text #15

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0511. Min Act: -0.1192

Data Index: 3313377 (Open Web Text)

Max Activating Token Index: 60

Text #16

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0573. Min Act: -0.1245

Data Index: 4098292 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0545. Min Act: -0.0944

Data Index: 1902706 (Open Web Text)

Max Activating Token Index: 36

Text #18

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0576. Min Act: -0.0822

Data Index: 4855838 (Open Web Text)

Max Activating Token Index: 48

Text #19

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0533. Min Act: -0.0995

Data Index: 4093948 (Open Web Text)

Max Activating Token Index: 46