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

Dataset: Open Web Text

Neuron 2128 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: 4.2310. Min Range: -4.2310

Max Act: 4.2310. Min Act: -0.1700

Data Index: 6045221 (Open Web Text)

Max Activating Token Index: 853

Text #1

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1972. Min Act: -0.1700

Data Index: 7747417 (Open Web Text)

Max Activating Token Index: 273

Text #2

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1929. Min Act: -0.1700

Data Index: 4658969 (Open Web Text)

Max Activating Token Index: 899

Text #3

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1606. Min Act: -0.1700

Data Index: 1902744 (Open Web Text)

Max Activating Token Index: 997

Text #4

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1813. Min Act: -0.1700

Data Index: 318978 (Open Web Text)

Max Activating Token Index: 945

Text #5

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1718. Min Act: -0.1700

Data Index: 7224084 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1360. Min Act: -0.1700

Data Index: 7895330 (Open Web Text)

Max Activating Token Index: 901

Text #7

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1288. Min Act: -0.1700

Data Index: 2494448 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1506. Min Act: -0.1700

Data Index: 6005205 (Open Web Text)

Max Activating Token Index: 909

Text #9

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1297. Min Act: -0.1700

Data Index: 8716370 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1513. Min Act: -0.1700

Data Index: 3929728 (Open Web Text)

Max Activating Token Index: 790

Text #11

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1558. Min Act: -0.1700

Data Index: 1669741 (Open Web Text)

Max Activating Token Index: 890

Text #12

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.0821. Min Act: -0.1700

Data Index: 8771445 (Open Web Text)

Max Activating Token Index: 761

Text #13

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1211. Min Act: -0.1700

Data Index: 4577632 (Open Web Text)

Max Activating Token Index: 367

Text #14

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.0784. Min Act: -0.1700

Data Index: 4982861 (Open Web Text)

Max Activating Token Index: 255

Text #15

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.0986. Min Act: -0.1700

Data Index: 7314744 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1024. Min Act: -0.1700

Data Index: 4849669 (Open Web Text)

Max Activating Token Index: 218

Text #17

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1042. Min Act: -0.1700

Data Index: 6696137 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1172. Min Act: -0.1700

Data Index: 4554399 (Open Web Text)

Max Activating Token Index: 744

Text #19

Max Range: 4.2310. Min Range: -4.2310

Max Act: 4.1042. Min Act: -0.1700

Data Index: 6284081 (Open Web Text)

Max Activating Token Index: 3