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

Dataset: Open Web Text

Neuron 653 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: 3.0024. Min Range: -3.0024

Max Act: 3.0024. Min Act: -0.1700

Data Index: 2047185 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.9539. Min Act: -0.1700

Data Index: 2574016 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8910. Min Act: -0.1700

Data Index: 6635495 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8874. Min Act: -0.1700

Data Index: 542109 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8841. Min Act: -0.1700

Data Index: 3025431 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8861. Min Act: -0.1700

Data Index: 2607624 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8868. Min Act: -0.1700

Data Index: 2943779 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8821. Min Act: -0.1700

Data Index: 966366 (Open Web Text)

Max Activating Token Index: 71

Text #8

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8649. Min Act: -0.1700

Data Index: 1153928 (Open Web Text)

Max Activating Token Index: 60

Text #9

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8746. Min Act: -0.1700

Data Index: 1153924 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8715. Min Act: -0.1700

Data Index: 1343734 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8448. Min Act: -0.1700

Data Index: 1153919 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8581. Min Act: -0.1700

Data Index: 7314703 (Open Web Text)

Max Activating Token Index: 863

Text #13

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8538. Min Act: -0.1700

Data Index: 8013867 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8450. Min Act: -0.1699

Data Index: 1153951 (Open Web Text)

Max Activating Token Index: 36

Text #15

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8548. Min Act: -0.1700

Data Index: 966368 (Open Web Text)

Max Activating Token Index: 65

Text #16

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8469. Min Act: -0.1700

Data Index: 1153933 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8507. Min Act: -0.1700

Data Index: 8300664 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8462. Min Act: -0.1700

Data Index: 966360 (Open Web Text)

Max Activating Token Index: 61

Text #19

Max Range: 3.0024. Min Range: -3.0024

Max Act: 2.8354. Min Act: -0.1700

Data Index: 6470727 (Open Web Text)

Max Activating Token Index: 391