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

Dataset: Open Web Text

Neuron 2131 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: 2.7004. Min Range: -2.7004

Max Act: 2.7004. Min Act: -0.1700

Data Index: 6682271 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6657. Min Act: -0.1700

Data Index: 8829171 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6740. Min Act: -0.1700

Data Index: 3365264 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6390. Min Act: -0.1700

Data Index: 4926090 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6358. Min Act: -0.1700

Data Index: 7579628 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6425. Min Act: -0.1700

Data Index: 5507916 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6143. Min Act: -0.1700

Data Index: 4491346 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6207. Min Act: -0.1700

Data Index: 8001767 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6144. Min Act: -0.1700

Data Index: 4015266 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6122. Min Act: -0.1700

Data Index: 4246622 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.5994. Min Act: -0.1700

Data Index: 8513058 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.5996. Min Act: -0.1700

Data Index: 8777667 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6123. Min Act: -0.1700

Data Index: 5207297 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.6050. Min Act: -0.1700

Data Index: 7079567 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.5867. Min Act: -0.1700

Data Index: 7503819 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.5860. Min Act: -0.1700

Data Index: 4189136 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.5936. Min Act: -0.1700

Data Index: 6763950 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.5987. Min Act: -0.1700

Data Index: 6071052 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.5899. Min Act: -0.1700

Data Index: 5981384 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.7004. Min Range: -2.7004

Max Act: 2.5876. Min Act: -0.1700

Data Index: 5276204 (Open Web Text)

Max Activating Token Index: 6