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

Dataset: Open Web Text

Neuron 2223 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: 4.6928. Min Range: -4.6928

Max Act: 4.6928. Min Act: -0.1700

Data Index: 69621 (Open Web Text)

Max Activating Token Index: 437

Text #1

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5803. Min Act: -0.1700

Data Index: 5010992 (Open Web Text)

Max Activating Token Index: 632

Text #2

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5549. Min Act: -0.1700

Data Index: 1672941 (Open Web Text)

Max Activating Token Index: 765

Text #3

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5856. Min Act: -0.1700

Data Index: 2255445 (Open Web Text)

Max Activating Token Index: 847

Text #4

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5734. Min Act: -0.1700

Data Index: 5606282 (Open Web Text)

Max Activating Token Index: 904

Text #5

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5269. Min Act: -0.1700

Data Index: 3600665 (Open Web Text)

Max Activating Token Index: 427

Text #6

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5025. Min Act: -0.1700

Data Index: 6590555 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5099. Min Act: -0.1700

Data Index: 903972 (Open Web Text)

Max Activating Token Index: 937

Text #8

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5112. Min Act: -0.1700

Data Index: 8425579 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5112. Min Act: -0.1700

Data Index: 3600664 (Open Web Text)

Max Activating Token Index: 825

Text #10

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5041. Min Act: -0.1700

Data Index: 830508 (Open Web Text)

Max Activating Token Index: 620

Text #11

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5006. Min Act: -0.1700

Data Index: 3907593 (Open Web Text)

Max Activating Token Index: 449

Text #12

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4771. Min Act: -0.1700

Data Index: 5795357 (Open Web Text)

Max Activating Token Index: 699

Text #13

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4827. Min Act: -0.1700

Data Index: 4761474 (Open Web Text)

Max Activating Token Index: 633

Text #14

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4640. Min Act: -0.1700

Data Index: 443969 (Open Web Text)

Max Activating Token Index: 852

Text #15

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4648. Min Act: -0.1700

Data Index: 5116850 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4338. Min Act: -0.1700

Data Index: 543511 (Open Web Text)

Max Activating Token Index: 553

Text #17

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4474. Min Act: -0.1700

Data Index: 3017474 (Open Web Text)

Max Activating Token Index: 584

Text #18

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4442. Min Act: -0.1700

Data Index: 2016628 (Open Web Text)

Max Activating Token Index: 837

Text #19

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4339. Min Act: -0.1700

Data Index: 1940103 (Open Web Text)

Max Activating Token Index: 606