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

Dataset: Open Web Text

Neuron 750 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: 3.4058. Min Range: -3.4058

Max Act: 3.4058. Min Act: -0.1700

Data Index: 6082041 (Open Web Text)

Max Activating Token Index: 721

Text #1

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.3606. Min Act: -0.1700

Data Index: 415512 (Open Web Text)

Max Activating Token Index: 971

Text #2

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.3136. Min Act: -0.1700

Data Index: 4203381 (Open Web Text)

Max Activating Token Index: 440

Text #3

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.2707. Min Act: -0.1700

Data Index: 7909753 (Open Web Text)

Max Activating Token Index: 343

Text #4

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.2812. Min Act: -0.1700

Data Index: 8539027 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.2739. Min Act: -0.1700

Data Index: 4087290 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.2729. Min Act: -0.1700

Data Index: 4231965 (Open Web Text)

Max Activating Token Index: 391

Text #7

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.2473. Min Act: -0.1700

Data Index: 5347170 (Open Web Text)

Max Activating Token Index: 425

Text #8

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.2180. Min Act: -0.1700

Data Index: 4355688 (Open Web Text)

Max Activating Token Index: 103

Text #9

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.1822. Min Act: -0.1700

Data Index: 3821830 (Open Web Text)

Max Activating Token Index: 879

Text #10

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.2030. Min Act: -0.1700

Data Index: 4850220 (Open Web Text)

Max Activating Token Index: 696

Text #11

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.2100. Min Act: -0.1700

Data Index: 5878849 (Open Web Text)

Max Activating Token Index: 732

Text #12

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.2019. Min Act: -0.1700

Data Index: 7523408 (Open Web Text)

Max Activating Token Index: 807

Text #13

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.1763. Min Act: -0.1700

Data Index: 5899069 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.1677. Min Act: -0.1700

Data Index: 7774861 (Open Web Text)

Max Activating Token Index: 646

Text #15

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.1644. Min Act: -0.1700

Data Index: 1337061 (Open Web Text)

Max Activating Token Index: 831

Text #16

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.1734. Min Act: -0.1700

Data Index: 4689162 (Open Web Text)

Max Activating Token Index: 942

Text #17

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.1743. Min Act: -0.1700

Data Index: 1491558 (Open Web Text)

Max Activating Token Index: 728

Text #18

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.1610. Min Act: -0.1700

Data Index: 846706 (Open Web Text)

Max Activating Token Index: 338

Text #19

Max Range: 3.4058. Min Range: -3.4058

Max Act: 3.1428. Min Act: -0.1700

Data Index: 6030630 (Open Web Text)

Max Activating Token Index: 264