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

Dataset: Open Web Text

Neuron 2580 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: 3.8254. Min Range: -3.8254

Max Act: 3.8248. Min Act: -0.1700

Data Index: 4045358 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.8254. Min Act: -0.1700

Data Index: 5342711 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.8201. Min Act: -0.1700

Data Index: 326796 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.7906. Min Act: -0.1700

Data Index: 6051247 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.7798. Min Act: -0.1700

Data Index: 7825272 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6961. Min Act: -0.1700

Data Index: 560148 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6978. Min Act: -0.1700

Data Index: 8449053 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.7080. Min Act: -0.1700

Data Index: 2276286 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6829. Min Act: -0.1700

Data Index: 4470466 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.7147. Min Act: -0.1700

Data Index: 4941584 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6582. Min Act: -0.1700

Data Index: 3618665 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6582. Min Act: -0.1700

Data Index: 5259204 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6582. Min Act: -0.1700

Data Index: 1542021 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6645. Min Act: -0.1700

Data Index: 4742705 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6593. Min Act: -0.1700

Data Index: 80793 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6852. Min Act: -0.1700

Data Index: 1484966 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6723. Min Act: -0.1700

Data Index: 2806735 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6582. Min Act: -0.1700

Data Index: 2777530 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6627. Min Act: -0.1700

Data Index: 4447655 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6722. Min Act: -0.1700

Data Index: 1898356 (Open Web Text)

Max Activating Token Index: 4