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

Dataset: Open Web Text

Neuron 2386 in Layer 2

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: 3.3004. Min Range: -3.3004

Max Act: 3.3004. Min Act: -0.1700

Data Index: 8783687 (Open Web Text)

Max Activating Token Index: 440

Text #1

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2074. Min Act: -0.1700

Data Index: 2079913 (Open Web Text)

Max Activating Token Index: 1019

Text #2

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2188. Min Act: -0.1700

Data Index: 1637916 (Open Web Text)

Max Activating Token Index: 887

Text #3

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1914. Min Act: -0.1700

Data Index: 2804662 (Open Web Text)

Max Activating Token Index: 492

Text #4

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1880. Min Act: -0.1700

Data Index: 1355007 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2231. Min Act: -0.1700

Data Index: 5983916 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2159. Min Act: -0.1700

Data Index: 4993301 (Open Web Text)

Max Activating Token Index: 491

Text #7

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1486. Min Act: -0.1700

Data Index: 3738151 (Open Web Text)

Max Activating Token Index: 856

Text #8

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1844. Min Act: -0.1700

Data Index: 811784 (Open Web Text)

Max Activating Token Index: 467

Text #9

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1806. Min Act: -0.1700

Data Index: 7115248 (Open Web Text)

Max Activating Token Index: 847

Text #10

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1914. Min Act: -0.1700

Data Index: 6165725 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1666. Min Act: -0.1700

Data Index: 962194 (Open Web Text)

Max Activating Token Index: 1000

Text #12

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1785. Min Act: -0.1700

Data Index: 7293059 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1925. Min Act: -0.1700

Data Index: 2937189 (Open Web Text)

Max Activating Token Index: 828

Text #14

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1906. Min Act: -0.1700

Data Index: 5500216 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1824. Min Act: -0.1700

Data Index: 681514 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1690. Min Act: -0.1700

Data Index: 2588012 (Open Web Text)

Max Activating Token Index: 453

Text #17

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1734. Min Act: -0.1700

Data Index: 478215 (Open Web Text)

Max Activating Token Index: 286

Text #18

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1687. Min Act: -0.1700

Data Index: 5466560 (Open Web Text)

Max Activating Token Index: 162

Text #19

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1853. Min Act: -0.1700

Data Index: 3789609 (Open Web Text)

Max Activating Token Index: 260