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

Dataset: Open Web Text

Neuron 1600 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: 4.6758. Min Range: -4.6758

Max Act: 4.6758. Min Act: -0.1700

Data Index: 6163301 (Open Web Text)

Max Activating Token Index: 452

Text #1

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.5669. Min Act: -0.1700

Data Index: 374118 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.5243. Min Act: -0.1700

Data Index: 395777 (Open Web Text)

Max Activating Token Index: 29

Text #3

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.5248. Min Act: -0.1700

Data Index: 1541927 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.5140. Min Act: -0.1700

Data Index: 3706924 (Open Web Text)

Max Activating Token Index: 592

Text #5

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.5274. Min Act: -0.1700

Data Index: 3011261 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4766. Min Act: -0.1700

Data Index: 4387530 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4795. Min Act: -0.1700

Data Index: 4369889 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4822. Min Act: -0.1700

Data Index: 4119839 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4813. Min Act: -0.1700

Data Index: 711108 (Open Web Text)

Max Activating Token Index: 468

Text #10

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4685. Min Act: -0.1700

Data Index: 4388115 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4768. Min Act: -0.1700

Data Index: 7362291 (Open Web Text)

Max Activating Token Index: 188

Text #12

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4717. Min Act: -0.1700

Data Index: 2247723 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4624. Min Act: -0.1700

Data Index: 3925625 (Open Web Text)

Max Activating Token Index: 203

Text #14

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4095. Min Act: -0.1700

Data Index: 395776 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4276. Min Act: -0.1700

Data Index: 3162383 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4314. Min Act: -0.1700

Data Index: 508415 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4352. Min Act: -0.1700

Data Index: 1647461 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4106. Min Act: -0.1700

Data Index: 5044008 (Open Web Text)

Max Activating Token Index: 625

Text #19

Max Range: 4.6758. Min Range: -4.6758

Max Act: 4.4293. Min Act: -0.1700

Data Index: 2654743 (Open Web Text)

Max Activating Token Index: 41