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

Dataset: Open Web Text

Neuron 1017 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: 4.9921. Min Range: -4.9921

Max Act: 4.9921. Min Act: -0.1700

Data Index: 8204209 (Open Web Text)

Max Activating Token Index: 699

Text #1

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.9233. Min Act: -0.1700

Data Index: 449909 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.8159. Min Act: -0.1700

Data Index: 1549749 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.8954. Min Act: -0.1700

Data Index: 8698554 (Open Web Text)

Max Activating Token Index: 615

Text #4

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.8842. Min Act: -0.1700

Data Index: 7561722 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.8524. Min Act: -0.1700

Data Index: 5591490 (Open Web Text)

Max Activating Token Index: 494

Text #6

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.8035. Min Act: -0.1700

Data Index: 8371466 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.8492. Min Act: -0.1700

Data Index: 2293107 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.7501. Min Act: -0.1700

Data Index: 2101544 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.8236. Min Act: -0.1700

Data Index: 6105982 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.8034. Min Act: -0.1700

Data Index: 1091641 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.7909. Min Act: -0.1700

Data Index: 5781794 (Open Web Text)

Max Activating Token Index: 354

Text #12

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.7584. Min Act: -0.1700

Data Index: 5065256 (Open Web Text)

Max Activating Token Index: 356

Text #13

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.7924. Min Act: -0.1700

Data Index: 1338094 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.6960. Min Act: -0.1700

Data Index: 6670313 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.6963. Min Act: -0.1700

Data Index: 4722843 (Open Web Text)

Max Activating Token Index: 183

Text #16

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.7173. Min Act: -0.1700

Data Index: 866156 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.7516. Min Act: -0.1700

Data Index: 1160070 (Open Web Text)

Max Activating Token Index: 783

Text #18

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.7410. Min Act: -0.1700

Data Index: 4443594 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 4.9921. Min Range: -4.9921

Max Act: 4.6933. Min Act: -0.1700

Data Index: 1549590 (Open Web Text)

Max Activating Token Index: 114