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

Dataset: Open Web Text

Neuron 1558 in Layer 2

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: 3.3203. Min Range: -3.3203

Max Act: 3.3203. Min Act: -0.1700

Data Index: 8755374 (Open Web Text)

Max Activating Token Index: 419

Text #1

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.2788. Min Act: -0.1700

Data Index: 3529763 (Open Web Text)

Max Activating Token Index: 446

Text #2

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1949. Min Act: -0.1700

Data Index: 2934968 (Open Web Text)

Max Activating Token Index: 952

Text #3

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1895. Min Act: -0.1700

Data Index: 6922415 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1891. Min Act: -0.1700

Data Index: 96742 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1728. Min Act: -0.1700

Data Index: 5933294 (Open Web Text)

Max Activating Token Index: 338

Text #6

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1561. Min Act: -0.1700

Data Index: 7087370 (Open Web Text)

Max Activating Token Index: 879

Text #7

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1088. Min Act: -0.1700

Data Index: 6410778 (Open Web Text)

Max Activating Token Index: 854

Text #8

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1333. Min Act: -0.1700

Data Index: 6640463 (Open Web Text)

Max Activating Token Index: 972

Text #9

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1319. Min Act: -0.1700

Data Index: 7091077 (Open Web Text)

Max Activating Token Index: 355

Text #10

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1293. Min Act: -0.1700

Data Index: 5029324 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1235. Min Act: -0.1700

Data Index: 8007891 (Open Web Text)

Max Activating Token Index: 531

Text #12

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1061. Min Act: -0.1700

Data Index: 5023276 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1208. Min Act: -0.1700

Data Index: 1889718 (Open Web Text)

Max Activating Token Index: 629

Text #14

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1016. Min Act: -0.1700

Data Index: 4069921 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0795. Min Act: -0.1700

Data Index: 232778 (Open Web Text)

Max Activating Token Index: 611

Text #16

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.1082. Min Act: -0.1700

Data Index: 1117318 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0749. Min Act: -0.1700

Data Index: 5405151 (Open Web Text)

Max Activating Token Index: 706

Text #18

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0747. Min Act: -0.1700

Data Index: 7024591 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 3.3203. Min Range: -3.3203

Max Act: 3.0508. Min Act: -0.1700

Data Index: 1277909 (Open Web Text)

Max Activating Token Index: 950