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

Dataset: Open Web Text

Neuron 1546 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: 3.0525. Min Range: -3.0525

Max Act: 3.0525. Min Act: -0.1700

Data Index: 4974552 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0186. Min Act: -0.1700

Data Index: 6481760 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0247. Min Act: -0.1700

Data Index: 1099642 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9993. Min Act: -0.1700

Data Index: 8041011 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0017. Min Act: -0.1700

Data Index: 1308512 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9967. Min Act: -0.1700

Data Index: 5922571 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9947. Min Act: -0.1700

Data Index: 319399 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0010. Min Act: -0.1700

Data Index: 1314274 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0044. Min Act: -0.1700

Data Index: 8223923 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9801. Min Act: -0.1700

Data Index: 5824486 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9754. Min Act: -0.1700

Data Index: 4698714 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9701. Min Act: -0.1700

Data Index: 5822698 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9666. Min Act: -0.1700

Data Index: 117420 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9569. Min Act: -0.1700

Data Index: 7623597 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9571. Min Act: -0.1700

Data Index: 1325605 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9482. Min Act: -0.1700

Data Index: 3882302 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9611. Min Act: -0.1700

Data Index: 7832070 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9458. Min Act: -0.1700

Data Index: 7994258 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9574. Min Act: -0.1700

Data Index: 5582572 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9578. Min Act: -0.1700

Data Index: 2467678 (Open Web Text)

Max Activating Token Index: 3