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

Dataset: Open Web Text

Neuron 1485 in Layer 1

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: 1.9925. Min Range: -1.9925

Max Act: 1.9925. Min Act: -0.1700

Data Index: 1164985 (Open Web Text)

Max Activating Token Index: 717

Text #1

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9822. Min Act: -0.1700

Data Index: 6129566 (Open Web Text)

Max Activating Token Index: 954

Text #2

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9750. Min Act: -0.1700

Data Index: 3244836 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9752. Min Act: -0.1700

Data Index: 2748863 (Open Web Text)

Max Activating Token Index: 989

Text #4

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9435. Min Act: -0.1700

Data Index: 6651077 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9335. Min Act: -0.1700

Data Index: 7206873 (Open Web Text)

Max Activating Token Index: 431

Text #6

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9356. Min Act: -0.1700

Data Index: 8046590 (Open Web Text)

Max Activating Token Index: 231

Text #7

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9191. Min Act: -0.1700

Data Index: 2520246 (Open Web Text)

Max Activating Token Index: 171

Text #8

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9036. Min Act: -0.1700

Data Index: 7593106 (Open Web Text)

Max Activating Token Index: 842

Text #9

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9205. Min Act: -0.1700

Data Index: 1945588 (Open Web Text)

Max Activating Token Index: 497

Text #10

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.9007. Min Act: -0.1700

Data Index: 4919664 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.8862. Min Act: -0.1700

Data Index: 4106550 (Open Web Text)

Max Activating Token Index: 840

Text #12

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.8979. Min Act: -0.1700

Data Index: 4086100 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.8999. Min Act: -0.1700

Data Index: 5672744 (Open Web Text)

Max Activating Token Index: 790

Text #14

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.8864. Min Act: -0.1700

Data Index: 3756439 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.8906. Min Act: -0.1700

Data Index: 7499287 (Open Web Text)

Max Activating Token Index: 973

Text #16

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.8912. Min Act: -0.1700

Data Index: 5915888 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.8917. Min Act: -0.1700

Data Index: 6040274 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.8755. Min Act: -0.1700

Data Index: 1055950 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 1.9925. Min Range: -1.9925

Max Act: 1.8717. Min Act: -0.1700

Data Index: 2753312 (Open Web Text)

Max Activating Token Index: 641