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

Dataset: Open Web Text

Neuron 2219 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: 2.6517. Min Range: -2.6517

Max Act: 2.6517. Min Act: -0.1700

Data Index: 5366558 (Open Web Text)

Max Activating Token Index: 86

Text #1

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.5640. Min Act: -0.1700

Data Index: 148305 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.5373. Min Act: -0.1700

Data Index: 2013816 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.5062. Min Act: -0.1700

Data Index: 6055754 (Open Web Text)

Max Activating Token Index: 379

Text #4

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.4787. Min Act: -0.1700

Data Index: 6800200 (Open Web Text)

Max Activating Token Index: 550

Text #5

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3837. Min Act: -0.1700

Data Index: 7113499 (Open Web Text)

Max Activating Token Index: 189

Text #6

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.4456. Min Act: -0.1700

Data Index: 1435533 (Open Web Text)

Max Activating Token Index: 386

Text #7

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.4310. Min Act: -0.1700

Data Index: 422662 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.4286. Min Act: -0.1700

Data Index: 6057030 (Open Web Text)

Max Activating Token Index: 445

Text #9

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.4092. Min Act: -0.1700

Data Index: 4220726 (Open Web Text)

Max Activating Token Index: 121

Text #10

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.4321. Min Act: -0.1700

Data Index: 4539636 (Open Web Text)

Max Activating Token Index: 900

Text #11

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3821. Min Act: -0.1700

Data Index: 361864 (Open Web Text)

Max Activating Token Index: 64

Text #12

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.4002. Min Act: -0.1700

Data Index: 1890690 (Open Web Text)

Max Activating Token Index: 98

Text #13

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3228. Min Act: -0.1700

Data Index: 101024 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3674. Min Act: -0.1700

Data Index: 1013737 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3533. Min Act: -0.1700

Data Index: 1807260 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3904. Min Act: -0.1700

Data Index: 2158517 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3180. Min Act: -0.1700

Data Index: 1101117 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.3780. Min Act: -0.1700

Data Index: 2560952 (Open Web Text)

Max Activating Token Index: 374

Text #19

Max Range: 2.6517. Min Range: -2.6517

Max Act: 2.2067. Min Act: -0.1700

Data Index: 943941 (Open Web Text)

Max Activating Token Index: 553