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

Dataset: Open Web Text

Neuron 346 in Layer 6

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: 4.9246. Min Range: -4.9246

Max Act: 4.9246. Min Act: -0.1700

Data Index: 8168856 (Open Web Text)

Max Activating Token Index: 869

Text #1

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.8184. Min Act: -0.1700

Data Index: 3924441 (Open Web Text)

Max Activating Token Index: 837

Text #2

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.7271. Min Act: -0.1700

Data Index: 1331963 (Open Web Text)

Max Activating Token Index: 485

Text #3

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.6792. Min Act: -0.1700

Data Index: 959228 (Open Web Text)

Max Activating Token Index: 670

Text #4

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.6477. Min Act: -0.1700

Data Index: 8572179 (Open Web Text)

Max Activating Token Index: 574

Text #5

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.5326. Min Act: -0.1700

Data Index: 5221983 (Open Web Text)

Max Activating Token Index: 435

Text #6

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.5314. Min Act: -0.1700

Data Index: 3831515 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.5030. Min Act: -0.1700

Data Index: 8654827 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.5029. Min Act: -0.1700

Data Index: 4328849 (Open Web Text)

Max Activating Token Index: 474

Text #9

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.4906. Min Act: -0.1700

Data Index: 414440 (Open Web Text)

Max Activating Token Index: 125

Text #10

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.4941. Min Act: -0.1700

Data Index: 7001267 (Open Web Text)

Max Activating Token Index: 90

Text #11

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.5100. Min Act: -0.1700

Data Index: 6156516 (Open Web Text)

Max Activating Token Index: 763

Text #12

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.4570. Min Act: -0.1700

Data Index: 102261 (Open Web Text)

Max Activating Token Index: 351

Text #13

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.4709. Min Act: -0.1700

Data Index: 7266504 (Open Web Text)

Max Activating Token Index: 728

Text #14

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.4914. Min Act: -0.1700

Data Index: 1034828 (Open Web Text)

Max Activating Token Index: 797

Text #15

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.4220. Min Act: -0.1700

Data Index: 4389782 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.4406. Min Act: -0.1700

Data Index: 5235180 (Open Web Text)

Max Activating Token Index: 264

Text #17

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.4748. Min Act: -0.1700

Data Index: 750400 (Open Web Text)

Max Activating Token Index: 903

Text #18

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.4034. Min Act: -0.1700

Data Index: 4518346 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 4.9246. Min Range: -4.9246

Max Act: 4.3957. Min Act: -0.1700

Data Index: 3721898 (Open Web Text)

Max Activating Token Index: 412