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

Dataset: Open Web Text

Neuron 2456 in Layer 5

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: 4.4518. Min Range: -4.4518

Max Act: 4.4518. Min Act: -0.1700

Data Index: 1096490 (Open Web Text)

Max Activating Token Index: 904

Text #1

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.4129. Min Act: -0.1700

Data Index: 5000681 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.3221. Min Act: -0.1700

Data Index: 5037558 (Open Web Text)

Max Activating Token Index: 250

Text #3

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2944. Min Act: -0.1700

Data Index: 7323093 (Open Web Text)

Max Activating Token Index: 443

Text #4

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2672. Min Act: -0.1700

Data Index: 6170658 (Open Web Text)

Max Activating Token Index: 836

Text #5

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2621. Min Act: -0.1700

Data Index: 3315250 (Open Web Text)

Max Activating Token Index: 80

Text #6

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2872. Min Act: -0.1700

Data Index: 2481525 (Open Web Text)

Max Activating Token Index: 890

Text #7

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2553. Min Act: -0.1700

Data Index: 1550799 (Open Web Text)

Max Activating Token Index: 467

Text #8

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2117. Min Act: -0.1700

Data Index: 7692487 (Open Web Text)

Max Activating Token Index: 591

Text #9

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1965. Min Act: -0.1700

Data Index: 4070162 (Open Web Text)

Max Activating Token Index: 913

Text #10

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2164. Min Act: -0.1700

Data Index: 7706018 (Open Web Text)

Max Activating Token Index: 622

Text #11

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2106. Min Act: -0.1700

Data Index: 5569421 (Open Web Text)

Max Activating Token Index: 153

Text #12

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1996. Min Act: -0.1700

Data Index: 2192627 (Open Web Text)

Max Activating Token Index: 739

Text #13

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1927. Min Act: -0.1700

Data Index: 7140133 (Open Web Text)

Max Activating Token Index: 106

Text #14

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2112. Min Act: -0.1700

Data Index: 3430042 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2036. Min Act: -0.1700

Data Index: 2930423 (Open Web Text)

Max Activating Token Index: 823

Text #16

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2235. Min Act: -0.1700

Data Index: 7579652 (Open Web Text)

Max Activating Token Index: 858

Text #17

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1754. Min Act: -0.1700

Data Index: 4543404 (Open Web Text)

Max Activating Token Index: 925

Text #18

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1693. Min Act: -0.1700

Data Index: 5701205 (Open Web Text)

Max Activating Token Index: 453

Text #19

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1628. Min Act: -0.1700

Data Index: 498090 (Open Web Text)

Max Activating Token Index: 945