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

Dataset: Open Web Text

Neuron 2735 in Layer 3

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: 3.0235. Min Range: -3.0235

Max Act: 2.9855. Min Act: -0.1700

Data Index: 6957116 (Open Web Text)

Max Activating Token Index: 1002

Text #1

Max Range: 3.0235. Min Range: -3.0235

Max Act: 3.0235. Min Act: -0.1700

Data Index: 5717979 (Open Web Text)

Max Activating Token Index: 785

Text #2

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.9702. Min Act: -0.1700

Data Index: 1798498 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.9315. Min Act: -0.1700

Data Index: 8303353 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8925. Min Act: -0.1700

Data Index: 7488741 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8925. Min Act: -0.1700

Data Index: 247238 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8925. Min Act: -0.1700

Data Index: 5429941 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8975. Min Act: -0.1700

Data Index: 6957118 (Open Web Text)

Max Activating Token Index: 688

Text #8

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8864. Min Act: -0.1700

Data Index: 8303355 (Open Web Text)

Max Activating Token Index: 452

Text #9

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8866. Min Act: -0.1700

Data Index: 6957106 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8691. Min Act: -0.1700

Data Index: 8303360 (Open Web Text)

Max Activating Token Index: 540

Text #11

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8705. Min Act: -0.1700

Data Index: 3935678 (Open Web Text)

Max Activating Token Index: 673

Text #12

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8710. Min Act: -0.1700

Data Index: 3935675 (Open Web Text)

Max Activating Token Index: 748

Text #13

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8757. Min Act: -0.1700

Data Index: 6957113 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8576. Min Act: -0.1700

Data Index: 3935669 (Open Web Text)

Max Activating Token Index: 1010

Text #15

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8465. Min Act: -0.1700

Data Index: 8201173 (Open Web Text)

Max Activating Token Index: 836

Text #16

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8475. Min Act: -0.1700

Data Index: 7168761 (Open Web Text)

Max Activating Token Index: 142

Text #17

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8362. Min Act: -0.1700

Data Index: 6643839 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8434. Min Act: -0.1700

Data Index: 6402204 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.0235. Min Range: -3.0235

Max Act: 2.8326. Min Act: -0.1700

Data Index: 6643844 (Open Web Text)

Max Activating Token Index: 995