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

Dataset: Open Web Text

Neuron 2749 in Layer 3

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: 4.6874. Min Range: -4.6874

Max Act: 4.6874. Min Act: -0.1700

Data Index: 2341241 (Open Web Text)

Max Activating Token Index: 542

Text #1

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.6661. Min Act: -0.1700

Data Index: 6332815 (Open Web Text)

Max Activating Token Index: 556

Text #2

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.6185. Min Act: -0.1700

Data Index: 5757271 (Open Web Text)

Max Activating Token Index: 362

Text #3

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5565. Min Act: -0.1700

Data Index: 7358546 (Open Web Text)

Max Activating Token Index: 264

Text #4

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5687. Min Act: -0.1700

Data Index: 4498800 (Open Web Text)

Max Activating Token Index: 409

Text #5

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5419. Min Act: -0.1700

Data Index: 1668695 (Open Web Text)

Max Activating Token Index: 631

Text #6

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5490. Min Act: -0.1700

Data Index: 1252886 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5044. Min Act: -0.1700

Data Index: 5474354 (Open Web Text)

Max Activating Token Index: 407

Text #8

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4877. Min Act: -0.1700

Data Index: 6932574 (Open Web Text)

Max Activating Token Index: 224

Text #9

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5418. Min Act: -0.1700

Data Index: 2012625 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5326. Min Act: -0.1700

Data Index: 267366 (Open Web Text)

Max Activating Token Index: 862

Text #11

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4838. Min Act: -0.1700

Data Index: 6245710 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4515. Min Act: -0.1700

Data Index: 4366807 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4784. Min Act: -0.1700

Data Index: 6125850 (Open Web Text)

Max Activating Token Index: 567

Text #14

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4850. Min Act: -0.1700

Data Index: 1442648 (Open Web Text)

Max Activating Token Index: 582

Text #15

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4734. Min Act: -0.1700

Data Index: 6932573 (Open Web Text)

Max Activating Token Index: 989

Text #16

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4446. Min Act: -0.1700

Data Index: 2463544 (Open Web Text)

Max Activating Token Index: 973

Text #17

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.5342. Min Act: -0.1700

Data Index: 6946649 (Open Web Text)

Max Activating Token Index: 325

Text #18

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4375. Min Act: -0.1700

Data Index: 5120235 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 4.6874. Min Range: -4.6874

Max Act: 4.4623. Min Act: -0.1700

Data Index: 5297536 (Open Web Text)

Max Activating Token Index: 891