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

Dataset: Open Web Text

Neuron 980 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: 4.3211. Min Range: -4.3211

Max Act: 4.3008. Min Act: -0.1700

Data Index: 574424 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.3211. Min Act: -0.1700

Data Index: 7242130 (Open Web Text)

Max Activating Token Index: 473

Text #2

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2957. Min Act: -0.1700

Data Index: 5643164 (Open Web Text)

Max Activating Token Index: 460

Text #3

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2954. Min Act: -0.1700

Data Index: 2058891 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2250. Min Act: -0.1700

Data Index: 5273031 (Open Web Text)

Max Activating Token Index: 464

Text #5

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2314. Min Act: -0.1700

Data Index: 7549297 (Open Web Text)

Max Activating Token Index: 480

Text #6

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2310. Min Act: -0.1700

Data Index: 7807732 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2371. Min Act: -0.1700

Data Index: 8737480 (Open Web Text)

Max Activating Token Index: 823

Text #8

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2276. Min Act: -0.1700

Data Index: 8737498 (Open Web Text)

Max Activating Token Index: 518

Text #9

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2030. Min Act: -0.1700

Data Index: 3146526 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2060. Min Act: -0.1700

Data Index: 4315959 (Open Web Text)

Max Activating Token Index: 907

Text #11

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.1864. Min Act: -0.1700

Data Index: 5820824 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.2141. Min Act: -0.1700

Data Index: 3166255 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.1449. Min Act: -0.1700

Data Index: 6002070 (Open Web Text)

Max Activating Token Index: 398

Text #14

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.1542. Min Act: -0.1700

Data Index: 507969 (Open Web Text)

Max Activating Token Index: 675

Text #15

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.1630. Min Act: -0.1700

Data Index: 1484395 (Open Web Text)

Max Activating Token Index: 567

Text #16

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.1520. Min Act: -0.1700

Data Index: 1546525 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.1573. Min Act: -0.1700

Data Index: 8110583 (Open Web Text)

Max Activating Token Index: 115

Text #18

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.1785. Min Act: -0.1700

Data Index: 2202094 (Open Web Text)

Max Activating Token Index: 77

Text #19

Max Range: 4.3211. Min Range: -4.3211

Max Act: 4.1374. Min Act: -0.1700

Data Index: 8653647 (Open Web Text)

Max Activating Token Index: 802