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

Dataset: Open Web Text

Neuron 3040 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: 3.3022. Min Range: -3.3022

Max Act: 3.3022. Min Act: -0.1700

Data Index: 7424808 (Open Web Text)

Max Activating Token Index: 905

Text #1

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.2558. Min Act: -0.1700

Data Index: 7358197 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.2410. Min Act: -0.1700

Data Index: 6328183 (Open Web Text)

Max Activating Token Index: 237

Text #3

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.2068. Min Act: -0.1700

Data Index: 854709 (Open Web Text)

Max Activating Token Index: 749

Text #4

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.2254. Min Act: -0.1700

Data Index: 1047278 (Open Web Text)

Max Activating Token Index: 773

Text #5

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.2137. Min Act: -0.1700

Data Index: 3993077 (Open Web Text)

Max Activating Token Index: 178

Text #6

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1951. Min Act: -0.1700

Data Index: 8283626 (Open Web Text)

Max Activating Token Index: 558

Text #7

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1690. Min Act: -0.1700

Data Index: 8278329 (Open Web Text)

Max Activating Token Index: 848

Text #8

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1734. Min Act: -0.1700

Data Index: 7503230 (Open Web Text)

Max Activating Token Index: 242

Text #9

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1553. Min Act: -0.1700

Data Index: 280900 (Open Web Text)

Max Activating Token Index: 685

Text #10

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1488. Min Act: -0.1700

Data Index: 1964254 (Open Web Text)

Max Activating Token Index: 790

Text #11

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1206. Min Act: -0.1700

Data Index: 3453315 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1225. Min Act: -0.1700

Data Index: 2165292 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1225. Min Act: -0.1700

Data Index: 3154299 (Open Web Text)

Max Activating Token Index: 854

Text #14

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1151. Min Act: -0.1700

Data Index: 3450655 (Open Web Text)

Max Activating Token Index: 910

Text #15

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1087. Min Act: -0.1700

Data Index: 2730785 (Open Web Text)

Max Activating Token Index: 531

Text #16

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.1148. Min Act: -0.1700

Data Index: 1964171 (Open Web Text)

Max Activating Token Index: 840

Text #17

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.0670. Min Act: -0.1700

Data Index: 4730933 (Open Web Text)

Max Activating Token Index: 734

Text #18

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.0880. Min Act: -0.1700

Data Index: 845190 (Open Web Text)

Max Activating Token Index: 26

Text #19

Max Range: 3.3022. Min Range: -3.3022

Max Act: 3.0766. Min Act: -0.1700

Data Index: 2036800 (Open Web Text)

Max Activating Token Index: 554