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

Dataset: Open Web Text

Neuron 1938 in Layer 4

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: 4.5255. Min Range: -4.5255

Max Act: 4.5255. Min Act: -0.1700

Data Index: 1037586 (Open Web Text)

Max Activating Token Index: 467

Text #1

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4716. Min Act: -0.1700

Data Index: 5399752 (Open Web Text)

Max Activating Token Index: 938

Text #2

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4527. Min Act: -0.1700

Data Index: 1915264 (Open Web Text)

Max Activating Token Index: 506

Text #3

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4379. Min Act: -0.1700

Data Index: 7764694 (Open Web Text)

Max Activating Token Index: 603

Text #4

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4931. Min Act: -0.1700

Data Index: 125023 (Open Web Text)

Max Activating Token Index: 449

Text #5

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4727. Min Act: -0.1700

Data Index: 910736 (Open Web Text)

Max Activating Token Index: 515

Text #6

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4202. Min Act: -0.1700

Data Index: 7824127 (Open Web Text)

Max Activating Token Index: 498

Text #7

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4622. Min Act: -0.1700

Data Index: 4153515 (Open Web Text)

Max Activating Token Index: 97

Text #8

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4356. Min Act: -0.1700

Data Index: 6891325 (Open Web Text)

Max Activating Token Index: 521

Text #9

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3947. Min Act: -0.1700

Data Index: 3319957 (Open Web Text)

Max Activating Token Index: 429

Text #10

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3898. Min Act: -0.1700

Data Index: 6437001 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3918. Min Act: -0.1700

Data Index: 5853087 (Open Web Text)

Max Activating Token Index: 693

Text #12

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3566. Min Act: -0.1700

Data Index: 1712725 (Open Web Text)

Max Activating Token Index: 428

Text #13

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3552. Min Act: -0.1700

Data Index: 5864655 (Open Web Text)

Max Activating Token Index: 561

Text #14

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3528. Min Act: -0.1700

Data Index: 4619783 (Open Web Text)

Max Activating Token Index: 944

Text #15

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3947. Min Act: -0.1700

Data Index: 4658484 (Open Web Text)

Max Activating Token Index: 84

Text #16

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3292. Min Act: -0.1700

Data Index: 4662376 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3550. Min Act: -0.1700

Data Index: 2876510 (Open Web Text)

Max Activating Token Index: 107

Text #18

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3675. Min Act: -0.1700

Data Index: 6149061 (Open Web Text)

Max Activating Token Index: 830

Text #19

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3390. Min Act: -0.1700

Data Index: 6159998 (Open Web Text)

Max Activating Token Index: 312