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

Dataset: Open Web Text

Neuron 2678 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: 6.0255. Min Range: -6.0255

Max Act: 6.0255. Min Act: -0.1700

Data Index: 4638764 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.9573. Min Act: -0.1700

Data Index: 8263752 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.9335. Min Act: -0.1700

Data Index: 8373867 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.9127. Min Act: -0.1700

Data Index: 5783928 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.9458. Min Act: -0.1700

Data Index: 5759039 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8929. Min Act: -0.1700

Data Index: 7027790 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8902. Min Act: -0.1700

Data Index: 5749722 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8748. Min Act: -0.1700

Data Index: 4359435 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8756. Min Act: -0.1700

Data Index: 8378880 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8657. Min Act: -0.1700

Data Index: 2375123 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8605. Min Act: -0.1700

Data Index: 7858634 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8535. Min Act: -0.1700

Data Index: 789056 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8731. Min Act: -0.1700

Data Index: 6843216 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8281. Min Act: -0.1700

Data Index: 4750706 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8266. Min Act: -0.1700

Data Index: 7795313 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8151. Min Act: -0.1700

Data Index: 6922820 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8488. Min Act: -0.1700

Data Index: 2941457 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8188. Min Act: -0.1700

Data Index: 6683996 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8166. Min Act: -0.1700

Data Index: 3687774 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 6.0255. Min Range: -6.0255

Max Act: 5.8153. Min Act: -0.1700

Data Index: 8534749 (Open Web Text)

Max Activating Token Index: 6