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

Dataset: Open Web Text

Neuron 858 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: 4.2100. Min Range: -4.2100

Max Act: 4.2100. Min Act: -0.1700

Data Index: 275740 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.2100. Min Range: -4.2100

Max Act: 4.1757. Min Act: -0.1700

Data Index: 1438246 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.2100. Min Range: -4.2100

Max Act: 4.1049. Min Act: -0.1700

Data Index: 6549834 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.2100. Min Range: -4.2100

Max Act: 4.0867. Min Act: -0.1700

Data Index: 8764371 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.2100. Min Range: -4.2100

Max Act: 4.0628. Min Act: -0.1700

Data Index: 2270027 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.2100. Min Range: -4.2100

Max Act: 4.0178. Min Act: -0.1700

Data Index: 7206307 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9914. Min Act: -0.1700

Data Index: 7922031 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9749. Min Act: -0.1700

Data Index: 217583 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9667. Min Act: -0.1700

Data Index: 1424366 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9741. Min Act: -0.1700

Data Index: 3199980 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9497. Min Act: -0.1700

Data Index: 5766615 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9413. Min Act: -0.1700

Data Index: 1754973 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9449. Min Act: -0.1700

Data Index: 5257803 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9586. Min Act: -0.1700

Data Index: 5669195 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9263. Min Act: -0.1700

Data Index: 3051781 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9160. Min Act: -0.1700

Data Index: 2194274 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9160. Min Act: -0.1700

Data Index: 4276030 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9303. Min Act: -0.1700

Data Index: 4052112 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9111. Min Act: -0.1700

Data Index: 3826953 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.2100. Min Range: -4.2100

Max Act: 3.9102. Min Act: -0.1700

Data Index: 636876 (Open Web Text)

Max Activating Token Index: 7