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

Dataset: Open Web Text

Neuron 1816 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: 3.9762. Min Range: -3.9762

Max Act: 3.9762. Min Act: -0.1700

Data Index: 4964123 (Open Web Text)

Max Activating Token Index: 396

Text #1

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.7081. Min Act: -0.1700

Data Index: 1699189 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.7203. Min Act: -0.1700

Data Index: 2188506 (Open Web Text)

Max Activating Token Index: 323

Text #3

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6717. Min Act: -0.1700

Data Index: 4964119 (Open Web Text)

Max Activating Token Index: 855

Text #4

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6596. Min Act: -0.1700

Data Index: 4063238 (Open Web Text)

Max Activating Token Index: 996

Text #5

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6012. Min Act: -0.1700

Data Index: 5008026 (Open Web Text)

Max Activating Token Index: 317

Text #6

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6125. Min Act: -0.1700

Data Index: 8438800 (Open Web Text)

Max Activating Token Index: 740

Text #7

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6117. Min Act: -0.1700

Data Index: 2900302 (Open Web Text)

Max Activating Token Index: 580

Text #8

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5899. Min Act: -0.1700

Data Index: 1719230 (Open Web Text)

Max Activating Token Index: 379

Text #9

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5860. Min Act: -0.1700

Data Index: 4964121 (Open Web Text)

Max Activating Token Index: 770

Text #10

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5453. Min Act: -0.1700

Data Index: 5428488 (Open Web Text)

Max Activating Token Index: 453

Text #11

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5382. Min Act: -0.1700

Data Index: 8647999 (Open Web Text)

Max Activating Token Index: 708

Text #12

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5189. Min Act: -0.1700

Data Index: 6459257 (Open Web Text)

Max Activating Token Index: 727

Text #13

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4900. Min Act: -0.1700

Data Index: 2846231 (Open Web Text)

Max Activating Token Index: 381

Text #14

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5003. Min Act: -0.1700

Data Index: 2188505 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4846. Min Act: -0.1700

Data Index: 5804259 (Open Web Text)

Max Activating Token Index: 325

Text #16

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4773. Min Act: -0.1700

Data Index: 4964126 (Open Web Text)

Max Activating Token Index: 776

Text #17

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4627. Min Act: -0.1700

Data Index: 5104790 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4621. Min Act: -0.1700

Data Index: 4964130 (Open Web Text)

Max Activating Token Index: 283

Text #19

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4651. Min Act: -0.1700

Data Index: 5008027 (Open Web Text)

Max Activating Token Index: 369