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

Dataset: Open Web Text

Neuron 2697 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: 4.6878. Min Range: -4.6878

Max Act: 4.6261. Min Act: -0.1700

Data Index: 8721741 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6725. Min Act: -0.1700

Data Index: 2574202 (Open Web Text)

Max Activating Token Index: 307

Text #2

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6782. Min Act: -0.1700

Data Index: 7406036 (Open Web Text)

Max Activating Token Index: 118

Text #3

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6878. Min Act: -0.1700

Data Index: 7712562 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6874. Min Act: -0.1700

Data Index: 1428392 (Open Web Text)

Max Activating Token Index: 253

Text #5

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6378. Min Act: -0.1700

Data Index: 5312313 (Open Web Text)

Max Activating Token Index: 754

Text #6

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6643. Min Act: -0.1700

Data Index: 741990 (Open Web Text)

Max Activating Token Index: 932

Text #7

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6256. Min Act: -0.1700

Data Index: 8153982 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6636. Min Act: -0.1700

Data Index: 3481453 (Open Web Text)

Max Activating Token Index: 703

Text #9

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6285. Min Act: -0.1700

Data Index: 6388689 (Open Web Text)

Max Activating Token Index: 239

Text #10

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6095. Min Act: -0.1700

Data Index: 5446455 (Open Web Text)

Max Activating Token Index: 504

Text #11

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6395. Min Act: -0.1700

Data Index: 4277276 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6176. Min Act: -0.1700

Data Index: 2317013 (Open Web Text)

Max Activating Token Index: 161

Text #13

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6090. Min Act: -0.1700

Data Index: 2858674 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.5930. Min Act: -0.1700

Data Index: 5669617 (Open Web Text)

Max Activating Token Index: 618

Text #15

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6352. Min Act: -0.1700

Data Index: 2171500 (Open Web Text)

Max Activating Token Index: 305

Text #16

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.5988. Min Act: -0.1700

Data Index: 2534178 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.5520. Min Act: -0.1700

Data Index: 6906342 (Open Web Text)

Max Activating Token Index: 480

Text #18

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6087. Min Act: -0.1700

Data Index: 4419137 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.6878. Min Range: -4.6878

Max Act: 4.6250. Min Act: -0.1700

Data Index: 1301837 (Open Web Text)

Max Activating Token Index: 251