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

Dataset: Open Web Text

Neuron 2714 in Layer 1

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: 1.5258. Min Range: -1.5258

Max Act: 1.5258. Min Act: -0.1700

Data Index: 3678035 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.5077. Min Act: -0.1700

Data Index: 7765205 (Open Web Text)

Max Activating Token Index: 657

Text #2

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.5079. Min Act: -0.1700

Data Index: 5830140 (Open Web Text)

Max Activating Token Index: 444

Text #3

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4902. Min Act: -0.1699

Data Index: 165395 (Open Web Text)

Max Activating Token Index: 108

Text #4

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4875. Min Act: -0.1700

Data Index: 1783686 (Open Web Text)

Max Activating Token Index: 101

Text #5

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4824. Min Act: -0.1700

Data Index: 2158740 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4801. Min Act: -0.1700

Data Index: 5718820 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4766. Min Act: -0.1700

Data Index: 165394 (Open Web Text)

Max Activating Token Index: 996

Text #8

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4723. Min Act: -0.1700

Data Index: 1990026 (Open Web Text)

Max Activating Token Index: 25

Text #9

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4669. Min Act: -0.1700

Data Index: 389887 (Open Web Text)

Max Activating Token Index: 635

Text #10

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4682. Min Act: -0.1700

Data Index: 5342900 (Open Web Text)

Max Activating Token Index: 504

Text #11

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4562. Min Act: -0.1699

Data Index: 1581013 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4548. Min Act: -0.1700

Data Index: 4171960 (Open Web Text)

Max Activating Token Index: 678

Text #13

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4455. Min Act: -0.1700

Data Index: 5365645 (Open Web Text)

Max Activating Token Index: 262

Text #14

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4546. Min Act: -0.1699

Data Index: 4240996 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4523. Min Act: -0.1700

Data Index: 5814434 (Open Web Text)

Max Activating Token Index: 430

Text #16

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4582. Min Act: -0.1700

Data Index: 6942682 (Open Web Text)

Max Activating Token Index: 718

Text #17

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4584. Min Act: -0.1700

Data Index: 1296872 (Open Web Text)

Max Activating Token Index: 219

Text #18

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4405. Min Act: -0.1699

Data Index: 3678033 (Open Web Text)

Max Activating Token Index: 194

Text #19

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4459. Min Act: -0.1700

Data Index: 5531028 (Open Web Text)

Max Activating Token Index: 15