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

Dataset: Open Web Text

Neuron 1051 in Layer 2

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: 2.3027. Min Range: -2.3027

Max Act: 2.3027. Min Act: -0.1700

Data Index: 7152457 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.3027. Min Act: -0.1700

Data Index: 6745120 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.3027. Min Act: -0.1700

Data Index: 6689577 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2723. Min Act: -0.1700

Data Index: 4260035 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2723. Min Act: -0.1700

Data Index: 6327702 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2723. Min Act: -0.1700

Data Index: 5029286 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2388. Min Act: -0.1700

Data Index: 7414572 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2361. Min Act: -0.1700

Data Index: 7809072 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2359. Min Act: -0.1700

Data Index: 7885588 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2464. Min Act: -0.1700

Data Index: 3422546 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2307. Min Act: -0.1700

Data Index: 7540626 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2082. Min Act: -0.1700

Data Index: 6984679 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2065. Min Act: -0.1700

Data Index: 2238625 (Open Web Text)

Max Activating Token Index: 31

Text #13

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.1941. Min Act: -0.1700

Data Index: 8725600 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.1918. Min Act: -0.1700

Data Index: 8520317 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.1690. Min Act: -0.1700

Data Index: 6709060 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.1702. Min Act: -0.1700

Data Index: 3307156 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.1728. Min Act: -0.1700

Data Index: 4393470 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.1880. Min Act: -0.1700

Data Index: 7690863 (Open Web Text)

Max Activating Token Index: 26

Text #19

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.1594. Min Act: -0.1700

Data Index: 3745046 (Open Web Text)

Max Activating Token Index: 4