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

Dataset: Open Web Text

Neuron 17 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: 2.9766. Min Range: -2.9766

Max Act: 2.9766. Min Act: -0.1700

Data Index: 286831 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.9700. Min Act: -0.1700

Data Index: 2997010 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.9360. Min Act: -0.1700

Data Index: 6607347 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.9330. Min Act: -0.1700

Data Index: 5156905 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.9284. Min Act: -0.1700

Data Index: 1793452 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.9054. Min Act: -0.1700

Data Index: 6717441 (Open Web Text)

Max Activating Token Index: 523

Text #6

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8957. Min Act: -0.1700

Data Index: 882304 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8966. Min Act: -0.1700

Data Index: 1018042 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8574. Min Act: -0.1700

Data Index: 3531701 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8636. Min Act: -0.1700

Data Index: 5161316 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8598. Min Act: -0.1700

Data Index: 7446849 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8637. Min Act: -0.1700

Data Index: 3555045 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8718. Min Act: -0.1700

Data Index: 7240232 (Open Web Text)

Max Activating Token Index: 213

Text #13

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8555. Min Act: -0.1700

Data Index: 7194844 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8588. Min Act: -0.1700

Data Index: 1513979 (Open Web Text)

Max Activating Token Index: 1010

Text #15

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8678. Min Act: -0.1700

Data Index: 2204916 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8586. Min Act: -0.1700

Data Index: 6942239 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8455. Min Act: -0.1700

Data Index: 3844261 (Open Web Text)

Max Activating Token Index: 298

Text #18

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8438. Min Act: -0.1700

Data Index: 5640179 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.9766. Min Range: -2.9766

Max Act: 2.8364. Min Act: -0.1700

Data Index: 2160759 (Open Web Text)

Max Activating Token Index: 4