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

Dataset: Open Web Text

Neuron 2537 in Layer 2

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: 3.1087. Min Range: -3.1087

Max Act: 3.1087. Min Act: -0.1700

Data Index: 6868287 (Open Web Text)

Max Activating Token Index: 596

Text #1

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0867. Min Act: -0.1700

Data Index: 4341247 (Open Web Text)

Max Activating Token Index: 633

Text #2

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.1021. Min Act: -0.1700

Data Index: 5704526 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0809. Min Act: -0.1700

Data Index: 2890746 (Open Web Text)

Max Activating Token Index: 582

Text #4

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0730. Min Act: -0.1700

Data Index: 5774237 (Open Web Text)

Max Activating Token Index: 852

Text #5

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0276. Min Act: -0.1700

Data Index: 3726561 (Open Web Text)

Max Activating Token Index: 974

Text #6

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0086. Min Act: -0.1700

Data Index: 3538662 (Open Web Text)

Max Activating Token Index: 774

Text #7

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.0109. Min Act: -0.1700

Data Index: 6889977 (Open Web Text)

Max Activating Token Index: 44

Text #8

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9973. Min Act: -0.1700

Data Index: 6026981 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9937. Min Act: -0.1700

Data Index: 5512305 (Open Web Text)

Max Activating Token Index: 33

Text #10

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9685. Min Act: -0.1700

Data Index: 6557093 (Open Web Text)

Max Activating Token Index: 1016

Text #11

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9678. Min Act: -0.1700

Data Index: 5768581 (Open Web Text)

Max Activating Token Index: 450

Text #12

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9701. Min Act: -0.1700

Data Index: 6295115 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9374. Min Act: -0.1700

Data Index: 1369737 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9275. Min Act: -0.1700

Data Index: 8013322 (Open Web Text)

Max Activating Token Index: 610

Text #15

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9107. Min Act: -0.1700

Data Index: 1216323 (Open Web Text)

Max Activating Token Index: 840

Text #16

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9385. Min Act: -0.1700

Data Index: 4935625 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9437. Min Act: -0.1700

Data Index: 7086656 (Open Web Text)

Max Activating Token Index: 432

Text #18

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.8967. Min Act: -0.1700

Data Index: 133406 (Open Web Text)

Max Activating Token Index: 765

Text #19

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.9173. Min Act: -0.1700

Data Index: 4425059 (Open Web Text)

Max Activating Token Index: 269