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

Dataset: Open Web Text

Neuron 2455 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: 1.6106. Min Range: -1.6106

Max Act: 1.6106. Min Act: -0.1700

Data Index: 2082652 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.6102. Min Act: -0.1700

Data Index: 8565332 (Open Web Text)

Max Activating Token Index: 375

Text #2

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.6056. Min Act: -0.1694

Data Index: 7414364 (Open Web Text)

Max Activating Token Index: 213

Text #3

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5687. Min Act: -0.1700

Data Index: 7309064 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5452. Min Act: -0.1699

Data Index: 2802514 (Open Web Text)

Max Activating Token Index: 948

Text #5

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5375. Min Act: -0.1700

Data Index: 8391297 (Open Web Text)

Max Activating Token Index: 307

Text #6

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5216. Min Act: -0.1700

Data Index: 8430981 (Open Web Text)

Max Activating Token Index: 638

Text #7

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5216. Min Act: -0.1699

Data Index: 3877821 (Open Web Text)

Max Activating Token Index: 858

Text #8

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5197. Min Act: -0.1700

Data Index: 3865713 (Open Web Text)

Max Activating Token Index: 583

Text #9

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5243. Min Act: -0.1700

Data Index: 1546220 (Open Web Text)

Max Activating Token Index: 660

Text #10

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5166. Min Act: -0.1700

Data Index: 3397766 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5300. Min Act: -0.1685

Data Index: 2144954 (Open Web Text)

Max Activating Token Index: 426

Text #12

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5095. Min Act: -0.1699

Data Index: 7791854 (Open Web Text)

Max Activating Token Index: 528

Text #13

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5084. Min Act: -0.1700

Data Index: 3873740 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5083. Min Act: -0.1697

Data Index: 84639 (Open Web Text)

Max Activating Token Index: 519

Text #15

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5037. Min Act: -0.1700

Data Index: 3640394 (Open Web Text)

Max Activating Token Index: 352

Text #16

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.4997. Min Act: -0.1699

Data Index: 2752856 (Open Web Text)

Max Activating Token Index: 354

Text #17

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5092. Min Act: -0.1695

Data Index: 1495331 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5066. Min Act: -0.1699

Data Index: 306104 (Open Web Text)

Max Activating Token Index: 243

Text #19

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.4996. Min Act: -0.1700

Data Index: 6552854 (Open Web Text)

Max Activating Token Index: 775