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

Dataset: Open Web Text

Neuron 1760 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: 3.3845. Min Range: -3.3845

Max Act: 3.3845. Min Act: -0.1700

Data Index: 8071015 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.3724. Min Act: -0.1700

Data Index: 7068312 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.3508. Min Act: -0.1700

Data Index: 986036 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.3144. Min Act: -0.1700

Data Index: 3085474 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2960. Min Act: -0.1700

Data Index: 4948969 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2738. Min Act: -0.1700

Data Index: 4207049 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2408. Min Act: -0.1700

Data Index: 3950860 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2719. Min Act: -0.1700

Data Index: 5902677 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2489. Min Act: -0.1700

Data Index: 1291560 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2242. Min Act: -0.1700

Data Index: 8312337 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2300. Min Act: -0.1700

Data Index: 4043662 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2162. Min Act: -0.1700

Data Index: 2730644 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2030. Min Act: -0.1700

Data Index: 5660636 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2024. Min Act: -0.1700

Data Index: 7479890 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2043. Min Act: -0.1700

Data Index: 2389229 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.1943. Min Act: -0.1700

Data Index: 7220264 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.1949. Min Act: -0.1700

Data Index: 8706725 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.1781. Min Act: -0.1700

Data Index: 8809036 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.2032. Min Act: -0.1700

Data Index: 4974568 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.3845. Min Range: -3.3845

Max Act: 3.1696. Min Act: -0.1700

Data Index: 1565663 (Open Web Text)

Max Activating Token Index: 7