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

Dataset: Open Web Text

Neuron 887 in Layer 4

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: 4.1663. Min Range: -4.1663

Max Act: 4.1663. Min Act: -0.1700

Data Index: 1358584 (Open Web Text)

Max Activating Token Index: 896

Text #1

Max Range: 4.1663. Min Range: -4.1663

Max Act: 4.1374. Min Act: -0.1700

Data Index: 3477516 (Open Web Text)

Max Activating Token Index: 998

Text #2

Max Range: 4.1663. Min Range: -4.1663

Max Act: 4.1252. Min Act: -0.1700

Data Index: 4229293 (Open Web Text)

Max Activating Token Index: 843

Text #3

Max Range: 4.1663. Min Range: -4.1663

Max Act: 4.0740. Min Act: -0.1700

Data Index: 2346083 (Open Web Text)

Max Activating Token Index: 892

Text #4

Max Range: 4.1663. Min Range: -4.1663

Max Act: 4.0166. Min Act: -0.1700

Data Index: 5354640 (Open Web Text)

Max Activating Token Index: 86

Text #5

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.9888. Min Act: -0.1700

Data Index: 2144850 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 4.1663. Min Range: -4.1663

Max Act: 4.0101. Min Act: -0.1700

Data Index: 8809296 (Open Web Text)

Max Activating Token Index: 983

Text #7

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.9859. Min Act: -0.1700

Data Index: 7164244 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.9000. Min Act: -0.1700

Data Index: 3926878 (Open Web Text)

Max Activating Token Index: 668

Text #9

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.9358. Min Act: -0.1700

Data Index: 6436218 (Open Web Text)

Max Activating Token Index: 848

Text #10

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.8853. Min Act: -0.1700

Data Index: 1427902 (Open Web Text)

Max Activating Token Index: 601

Text #11

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.8463. Min Act: -0.1700

Data Index: 2310969 (Open Web Text)

Max Activating Token Index: 137

Text #12

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.7904. Min Act: -0.1700

Data Index: 5842734 (Open Web Text)

Max Activating Token Index: 774

Text #13

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.8164. Min Act: -0.1700

Data Index: 7749012 (Open Web Text)

Max Activating Token Index: 780

Text #14

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.8043. Min Act: -0.1700

Data Index: 6592630 (Open Web Text)

Max Activating Token Index: 242

Text #15

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.7762. Min Act: -0.1700

Data Index: 6818175 (Open Web Text)

Max Activating Token Index: 65

Text #16

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.7649. Min Act: -0.1700

Data Index: 6035456 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.7418. Min Act: -0.1700

Data Index: 5514142 (Open Web Text)

Max Activating Token Index: 187

Text #18

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.7159. Min Act: -0.1700

Data Index: 506861 (Open Web Text)

Max Activating Token Index: 968

Text #19

Max Range: 4.1663. Min Range: -4.1663

Max Act: 3.7096. Min Act: -0.1700

Data Index: 6232321 (Open Web Text)

Max Activating Token Index: 101