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

Dataset: Open Web Text

Neuron 396 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: 4.7735. Min Range: -4.7735

Max Act: 4.7735. Min Act: -0.1700

Data Index: 8620492 (Open Web Text)

Max Activating Token Index: 495

Text #1

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.7585. Min Act: -0.1700

Data Index: 3577358 (Open Web Text)

Max Activating Token Index: 635

Text #2

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.7310. Min Act: -0.1700

Data Index: 3891886 (Open Web Text)

Max Activating Token Index: 150

Text #3

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.5354. Min Act: -0.1700

Data Index: 7869700 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.4754. Min Act: -0.1700

Data Index: 5742121 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.4946. Min Act: -0.1700

Data Index: 2146619 (Open Web Text)

Max Activating Token Index: 711

Text #6

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.4772. Min Act: -0.1700

Data Index: 5604850 (Open Web Text)

Max Activating Token Index: 766

Text #7

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.4429. Min Act: -0.1700

Data Index: 6876579 (Open Web Text)

Max Activating Token Index: 656

Text #8

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.4269. Min Act: -0.1700

Data Index: 1199153 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.4175. Min Act: -0.1700

Data Index: 3501453 (Open Web Text)

Max Activating Token Index: 86

Text #10

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.3846. Min Act: -0.1700

Data Index: 414525 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.3763. Min Act: -0.1700

Data Index: 5340646 (Open Web Text)

Max Activating Token Index: 744

Text #12

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.4023. Min Act: -0.1700

Data Index: 5570164 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.3626. Min Act: -0.1700

Data Index: 2631278 (Open Web Text)

Max Activating Token Index: 1004

Text #14

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.3463. Min Act: -0.1700

Data Index: 4674703 (Open Web Text)

Max Activating Token Index: 656

Text #15

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.3507. Min Act: -0.1700

Data Index: 7149263 (Open Web Text)

Max Activating Token Index: 826

Text #16

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.3630. Min Act: -0.1700

Data Index: 7081319 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.3691. Min Act: -0.1700

Data Index: 4225358 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.3743. Min Act: -0.1700

Data Index: 2682083 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 4.7735. Min Range: -4.7735

Max Act: 4.3605. Min Act: -0.1700

Data Index: 1353560 (Open Web Text)

Max Activating Token Index: 763