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

Dataset: Open Web Text

Neuron 905 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: 3.9855. Min Range: -3.9855

Max Act: 3.9751. Min Act: -0.1700

Data Index: 4423112 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.9855. Min Act: -0.1700

Data Index: 8415202 (Open Web Text)

Max Activating Token Index: 510

Text #2

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.9649. Min Act: -0.1700

Data Index: 5737087 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.9774. Min Act: -0.1700

Data Index: 1624573 (Open Web Text)

Max Activating Token Index: 849

Text #4

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.9670. Min Act: -0.1700

Data Index: 436955 (Open Web Text)

Max Activating Token Index: 51

Text #5

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.9349. Min Act: -0.1700

Data Index: 7968581 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.9300. Min Act: -0.1700

Data Index: 85327 (Open Web Text)

Max Activating Token Index: 827

Text #7

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.9065. Min Act: -0.1700

Data Index: 8008260 (Open Web Text)

Max Activating Token Index: 361

Text #8

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8672. Min Act: -0.1700

Data Index: 8492262 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8989. Min Act: -0.1700

Data Index: 5192895 (Open Web Text)

Max Activating Token Index: 452

Text #10

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8667. Min Act: -0.1700

Data Index: 1561819 (Open Web Text)

Max Activating Token Index: 214

Text #11

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8728. Min Act: -0.1700

Data Index: 5998454 (Open Web Text)

Max Activating Token Index: 626

Text #12

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8788. Min Act: -0.1700

Data Index: 6646700 (Open Web Text)

Max Activating Token Index: 222

Text #13

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8805. Min Act: -0.1700

Data Index: 4791332 (Open Web Text)

Max Activating Token Index: 816

Text #14

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8688. Min Act: -0.1700

Data Index: 3538595 (Open Web Text)

Max Activating Token Index: 495

Text #15

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8781. Min Act: -0.1700

Data Index: 2496885 (Open Web Text)

Max Activating Token Index: 859

Text #16

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.9030. Min Act: -0.1700

Data Index: 2675630 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8587. Min Act: -0.1700

Data Index: 5199666 (Open Web Text)

Max Activating Token Index: 156

Text #18

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8173. Min Act: -0.1700

Data Index: 4958247 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 3.9855. Min Range: -3.9855

Max Act: 3.8159. Min Act: -0.1700

Data Index: 4679798 (Open Web Text)

Max Activating Token Index: 1022