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

Dataset: Open Web Text

Neuron 2572 in Layer 5

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: 4.6774. Min Range: -4.6774

Max Act: 4.6550. Min Act: -0.1700

Data Index: 5759201 (Open Web Text)

Max Activating Token Index: 814

Text #1

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.6774. Min Act: -0.1700

Data Index: 7943860 (Open Web Text)

Max Activating Token Index: 797

Text #2

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.6697. Min Act: -0.1700

Data Index: 8060347 (Open Web Text)

Max Activating Token Index: 411

Text #3

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.6433. Min Act: -0.1700

Data Index: 3465827 (Open Web Text)

Max Activating Token Index: 328

Text #4

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.6236. Min Act: -0.1700

Data Index: 1146649 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5900. Min Act: -0.1700

Data Index: 4640782 (Open Web Text)

Max Activating Token Index: 549

Text #6

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.6051. Min Act: -0.1700

Data Index: 8415823 (Open Web Text)

Max Activating Token Index: 81

Text #7

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5787. Min Act: -0.1700

Data Index: 3187121 (Open Web Text)

Max Activating Token Index: 942

Text #8

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5929. Min Act: -0.1700

Data Index: 4772303 (Open Web Text)

Max Activating Token Index: 766

Text #9

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5593. Min Act: -0.1700

Data Index: 1204079 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5211. Min Act: -0.1700

Data Index: 7799690 (Open Web Text)

Max Activating Token Index: 682

Text #11

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5615. Min Act: -0.1700

Data Index: 1671806 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5352. Min Act: -0.1700

Data Index: 6670201 (Open Web Text)

Max Activating Token Index: 651

Text #13

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5271. Min Act: -0.1700

Data Index: 4143258 (Open Web Text)

Max Activating Token Index: 82

Text #14

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5090. Min Act: -0.1700

Data Index: 7086326 (Open Web Text)

Max Activating Token Index: 783

Text #15

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5032. Min Act: -0.1700

Data Index: 7358591 (Open Web Text)

Max Activating Token Index: 903

Text #16

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.4775. Min Act: -0.1700

Data Index: 4523476 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5258. Min Act: -0.1700

Data Index: 5667168 (Open Web Text)

Max Activating Token Index: 480

Text #18

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5176. Min Act: -0.1700

Data Index: 1631970 (Open Web Text)

Max Activating Token Index: 343

Text #19

Max Range: 4.6774. Min Range: -4.6774

Max Act: 4.5008. Min Act: -0.1700

Data Index: 4030074 (Open Web Text)

Max Activating Token Index: 681