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

Dataset: Open Web Text

Neuron 2013 in Layer 0

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: 3.5660. Min Range: -3.5660

Max Act: 3.5474. Min Act: -0.1700

Data Index: 5848851 (Open Web Text)

Max Activating Token Index: 807

Text #1

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.5571. Min Act: -0.1700

Data Index: 4270044 (Open Web Text)

Max Activating Token Index: 123

Text #2

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.5659. Min Act: -0.1700

Data Index: 1725827 (Open Web Text)

Max Activating Token Index: 785

Text #3

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.5660. Min Act: -0.1700

Data Index: 1224174 (Open Web Text)

Max Activating Token Index: 150

Text #4

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.5544. Min Act: -0.1700

Data Index: 5602258 (Open Web Text)

Max Activating Token Index: 656

Text #5

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.5346. Min Act: -0.1700

Data Index: 2561734 (Open Web Text)

Max Activating Token Index: 385

Text #6

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4884. Min Act: -0.1700

Data Index: 974843 (Open Web Text)

Max Activating Token Index: 384

Text #7

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.5077. Min Act: -0.1700

Data Index: 3346684 (Open Web Text)

Max Activating Token Index: 915

Text #8

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4706. Min Act: -0.1700

Data Index: 4960534 (Open Web Text)

Max Activating Token Index: 816

Text #9

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4702. Min Act: -0.1700

Data Index: 885792 (Open Web Text)

Max Activating Token Index: 594

Text #10

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4599. Min Act: -0.1700

Data Index: 5310444 (Open Web Text)

Max Activating Token Index: 704

Text #11

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4511. Min Act: -0.1700

Data Index: 4649834 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4438. Min Act: -0.1700

Data Index: 2192461 (Open Web Text)

Max Activating Token Index: 78

Text #13

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4556. Min Act: -0.1700

Data Index: 5573652 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4069. Min Act: -0.1700

Data Index: 621321 (Open Web Text)

Max Activating Token Index: 241

Text #15

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.3856. Min Act: -0.1700

Data Index: 3448715 (Open Web Text)

Max Activating Token Index: 630

Text #16

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4205. Min Act: -0.1700

Data Index: 4173248 (Open Web Text)

Max Activating Token Index: 708

Text #17

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4232. Min Act: -0.1700

Data Index: 2845930 (Open Web Text)

Max Activating Token Index: 387

Text #18

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4080. Min Act: -0.1700

Data Index: 977747 (Open Web Text)

Max Activating Token Index: 884

Text #19

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4030. Min Act: -0.1700

Data Index: 10255 (Open Web Text)

Max Activating Token Index: 270