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

Dataset: Open Web Text

Neuron 2016 in Layer 5

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: 4.0195. Min Range: -4.0195

Max Act: 4.0195. Min Act: -0.1700

Data Index: 579669 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.9741. Min Act: -0.1700

Data Index: 579653 (Open Web Text)

Max Activating Token Index: 198

Text #2

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.9410. Min Act: -0.1700

Data Index: 3006405 (Open Web Text)

Max Activating Token Index: 396

Text #3

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8757. Min Act: -0.1700

Data Index: 4632269 (Open Web Text)

Max Activating Token Index: 528

Text #4

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8973. Min Act: -0.1700

Data Index: 579667 (Open Web Text)

Max Activating Token Index: 278

Text #5

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8884. Min Act: -0.1700

Data Index: 579648 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8830. Min Act: -0.1700

Data Index: 579665 (Open Web Text)

Max Activating Token Index: 725

Text #7

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.9168. Min Act: -0.1700

Data Index: 2278794 (Open Web Text)

Max Activating Token Index: 93

Text #8

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.9033. Min Act: -0.1700

Data Index: 579666 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8882. Min Act: -0.1700

Data Index: 579661 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8772. Min Act: -0.1700

Data Index: 4856052 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8703. Min Act: -0.1700

Data Index: 2636640 (Open Web Text)

Max Activating Token Index: 153

Text #12

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8621. Min Act: -0.1700

Data Index: 579650 (Open Web Text)

Max Activating Token Index: 93

Text #13

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8401. Min Act: -0.1700

Data Index: 579656 (Open Web Text)

Max Activating Token Index: 327

Text #14

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8411. Min Act: -0.1700

Data Index: 579659 (Open Web Text)

Max Activating Token Index: 143

Text #15

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8556. Min Act: -0.1700

Data Index: 579655 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8513. Min Act: -0.1700

Data Index: 579664 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8496. Min Act: -0.1700

Data Index: 579662 (Open Web Text)

Max Activating Token Index: 438

Text #18

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8378. Min Act: -0.1700

Data Index: 3199602 (Open Web Text)

Max Activating Token Index: 754

Text #19

Max Range: 4.0195. Min Range: -4.0195

Max Act: 3.8222. Min Act: -0.1700

Data Index: 4692974 (Open Web Text)

Max Activating Token Index: 379