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

Dataset: Open Web Text

Neuron 2819 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: 4.9535. Min Range: -4.9535

Max Act: 4.9535. Min Act: -0.1700

Data Index: 4102785 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.9234. Min Act: -0.1700

Data Index: 5167634 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8793. Min Act: -0.1700

Data Index: 1853168 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8637. Min Act: -0.1700

Data Index: 3781634 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8771. Min Act: -0.1700

Data Index: 3237930 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8336. Min Act: -0.1700

Data Index: 3430529 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8469. Min Act: -0.1700

Data Index: 7719989 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8518. Min Act: -0.1700

Data Index: 102861 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8320. Min Act: -0.1700

Data Index: 1769158 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8336. Min Act: -0.1700

Data Index: 4612601 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8276. Min Act: -0.1700

Data Index: 3630147 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8508. Min Act: -0.1700

Data Index: 5955251 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8330. Min Act: -0.1700

Data Index: 4255874 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8050. Min Act: -0.1700

Data Index: 3610719 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8259. Min Act: -0.1700

Data Index: 416072 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8168. Min Act: -0.1700

Data Index: 1534922 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8077. Min Act: -0.1700

Data Index: 491705 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8120. Min Act: -0.1700

Data Index: 4106032 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8039. Min Act: -0.1700

Data Index: 1639370 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.9535. Min Range: -4.9535

Max Act: 4.8004. Min Act: -0.1700

Data Index: 2463243 (Open Web Text)

Max Activating Token Index: 5