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

Dataset: Open Web Text

Neuron 2216 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: 0.9315. Min Range: -0.9315

Max Act: 0.9315. Min Act: -0.1700

Data Index: 7220275 (Open Web Text)

Max Activating Token Index: 516

Text #1

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.9160. Min Act: -0.1700

Data Index: 2343163 (Open Web Text)

Max Activating Token Index: 542

Text #2

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.9046. Min Act: -0.1700

Data Index: 568002 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8993. Min Act: -0.1700

Data Index: 8823060 (Open Web Text)

Max Activating Token Index: 516

Text #4

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.9022. Min Act: -0.1700

Data Index: 2383370 (Open Web Text)

Max Activating Token Index: 532

Text #5

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.9024. Min Act: -0.1700

Data Index: 4623444 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8908. Min Act: -0.1700

Data Index: 3320890 (Open Web Text)

Max Activating Token Index: 518

Text #7

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.9007. Min Act: -0.1700

Data Index: 6861135 (Open Web Text)

Max Activating Token Index: 535

Text #8

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8880. Min Act: -0.1700

Data Index: 2951475 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8996. Min Act: -0.1700

Data Index: 6131330 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8953. Min Act: -0.1700

Data Index: 7830491 (Open Web Text)

Max Activating Token Index: 516

Text #11

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8884. Min Act: -0.1700

Data Index: 455013 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8883. Min Act: -0.1700

Data Index: 6251600 (Open Web Text)

Max Activating Token Index: 516

Text #13

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8874. Min Act: -0.1700

Data Index: 6110819 (Open Web Text)

Max Activating Token Index: 537

Text #14

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8889. Min Act: -0.1700

Data Index: 1429355 (Open Web Text)

Max Activating Token Index: 521

Text #15

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8771. Min Act: -0.1700

Data Index: 661726 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8794. Min Act: -0.1700

Data Index: 3577551 (Open Web Text)

Max Activating Token Index: 529

Text #17

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8750. Min Act: -0.1700

Data Index: 5983743 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8753. Min Act: -0.1700

Data Index: 5833584 (Open Web Text)

Max Activating Token Index: 525

Text #19

Max Range: 0.9315. Min Range: -0.9315

Max Act: 0.8770. Min Act: -0.1700

Data Index: 5474936 (Open Web Text)

Max Activating Token Index: 536