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

Dataset: Open Web Text

Neuron 2124 in Layer 4

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: 3.8792. Min Range: -3.8792

Max Act: 3.8792. Min Act: -0.1700

Data Index: 5695811 (Open Web Text)

Max Activating Token Index: 450

Text #1

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.8268. Min Act: -0.1700

Data Index: 2655244 (Open Web Text)

Max Activating Token Index: 299

Text #2

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.7657. Min Act: -0.1700

Data Index: 3691434 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.7378. Min Act: -0.1700

Data Index: 4574229 (Open Web Text)

Max Activating Token Index: 846

Text #4

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.7350. Min Act: -0.1700

Data Index: 960843 (Open Web Text)

Max Activating Token Index: 520

Text #5

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.7270. Min Act: -0.1700

Data Index: 4003797 (Open Web Text)

Max Activating Token Index: 37

Text #6

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.6698. Min Act: -0.1700

Data Index: 6654710 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.6403. Min Act: -0.1700

Data Index: 6834724 (Open Web Text)

Max Activating Token Index: 269

Text #8

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.6315. Min Act: -0.1700

Data Index: 5330928 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.6338. Min Act: -0.1700

Data Index: 1360571 (Open Web Text)

Max Activating Token Index: 764

Text #10

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.6199. Min Act: -0.1700

Data Index: 3446835 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.6252. Min Act: -0.1700

Data Index: 1622258 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.6564. Min Act: -0.1700

Data Index: 3410488 (Open Web Text)

Max Activating Token Index: 631

Text #13

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.5895. Min Act: -0.1700

Data Index: 4512411 (Open Web Text)

Max Activating Token Index: 884

Text #14

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.6173. Min Act: -0.1700

Data Index: 5092787 (Open Web Text)

Max Activating Token Index: 339

Text #15

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.6131. Min Act: -0.1700

Data Index: 7563869 (Open Web Text)

Max Activating Token Index: 818

Text #16

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.5835. Min Act: -0.1700

Data Index: 6367723 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.5929. Min Act: -0.1700

Data Index: 5847029 (Open Web Text)

Max Activating Token Index: 43

Text #18

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.5691. Min Act: -0.1700

Data Index: 6708754 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 3.8792. Min Range: -3.8792

Max Act: 3.5996. Min Act: -0.1700

Data Index: 1845194 (Open Web Text)

Max Activating Token Index: 163