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

Dataset: Open Web Text

Neuron 84 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: 4.9013. Min Range: -4.9013

Max Act: 4.8812. Min Act: -0.1700

Data Index: 7002120 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.9011. Min Act: -0.1700

Data Index: 7912168 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.9013. Min Act: -0.1700

Data Index: 3721907 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8690. Min Act: -0.1700

Data Index: 2130667 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8932. Min Act: -0.1700

Data Index: 6690767 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8636. Min Act: -0.1700

Data Index: 2575743 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8465. Min Act: -0.1700

Data Index: 3310877 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8412. Min Act: -0.1700

Data Index: 3566205 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8005. Min Act: -0.1700

Data Index: 2102282 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8047. Min Act: -0.1700

Data Index: 6647708 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8211. Min Act: -0.1700

Data Index: 3843112 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8058. Min Act: -0.1700

Data Index: 1495094 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.7967. Min Act: -0.1700

Data Index: 3600130 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.7977. Min Act: -0.1700

Data Index: 1119351 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8175. Min Act: -0.1700

Data Index: 3371230 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.8038. Min Act: -0.1700

Data Index: 6417051 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.7935. Min Act: -0.1700

Data Index: 4529170 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.7696. Min Act: -0.1700

Data Index: 429627 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.7607. Min Act: -0.1700

Data Index: 6516512 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.9013. Min Range: -4.9013

Max Act: 4.7884. Min Act: -0.1700

Data Index: 3266194 (Open Web Text)

Max Activating Token Index: 5