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

Dataset: Open Web Text

Neuron 616 in Layer 2

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: 5.4326. Min Range: -5.4326

Max Act: 5.4326. Min Act: -0.1700

Data Index: 6590772 (Open Web Text)

Max Activating Token Index: 198

Text #1

Max Range: 5.4326. Min Range: -5.4326

Max Act: 5.3667. Min Act: -0.1700

Data Index: 7067737 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 5.4326. Min Range: -5.4326

Max Act: 5.3266. Min Act: -0.1700

Data Index: 7891683 (Open Web Text)

Max Activating Token Index: 349

Text #3

Max Range: 5.4326. Min Range: -5.4326

Max Act: 5.2494. Min Act: -0.1700

Data Index: 4726904 (Open Web Text)

Max Activating Token Index: 312

Text #4

Max Range: 5.4326. Min Range: -5.4326

Max Act: 5.1489. Min Act: -0.1700

Data Index: 8118705 (Open Web Text)

Max Activating Token Index: 148

Text #5

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.9613. Min Act: -0.1700

Data Index: 4514742 (Open Web Text)

Max Activating Token Index: 91

Text #6

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.9395. Min Act: -0.1700

Data Index: 5768758 (Open Web Text)

Max Activating Token Index: 587

Text #7

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.9545. Min Act: -0.1700

Data Index: 706374 (Open Web Text)

Max Activating Token Index: 82

Text #8

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.9800. Min Act: -0.1700

Data Index: 3158050 (Open Web Text)

Max Activating Token Index: 244

Text #9

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.9929. Min Act: -0.1700

Data Index: 7385687 (Open Web Text)

Max Activating Token Index: 413

Text #10

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.9090. Min Act: -0.1700

Data Index: 4237131 (Open Web Text)

Max Activating Token Index: 873

Text #11

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.8849. Min Act: -0.1699

Data Index: 1997882 (Open Web Text)

Max Activating Token Index: 842

Text #12

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.8850. Min Act: -0.1700

Data Index: 5517902 (Open Web Text)

Max Activating Token Index: 365

Text #13

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.8708. Min Act: -0.1700

Data Index: 8805160 (Open Web Text)

Max Activating Token Index: 388

Text #14

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.8743. Min Act: -0.1700

Data Index: 8598132 (Open Web Text)

Max Activating Token Index: 339

Text #15

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.8881. Min Act: -0.1700

Data Index: 4734681 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.8412. Min Act: -0.1700

Data Index: 2728772 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.8559. Min Act: -0.1700

Data Index: 488863 (Open Web Text)

Max Activating Token Index: 333

Text #18

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.8237. Min Act: -0.1700

Data Index: 224598 (Open Web Text)

Max Activating Token Index: 697

Text #19

Max Range: 5.4326. Min Range: -5.4326

Max Act: 4.7990. Min Act: -0.1700

Data Index: 4411869 (Open Web Text)

Max Activating Token Index: 683