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

Dataset: Open Web Text

Neuron 1365 in Layer 6

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: 5.7928. Min Range: -5.7928

Max Act: 5.7928. Min Act: -0.1700

Data Index: 4305444 (Open Web Text)

Max Activating Token Index: 941

Text #1

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.4823. Min Act: -0.1700

Data Index: 344883 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.4403. Min Act: -0.1700

Data Index: 7816959 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.4327. Min Act: -0.1700

Data Index: 1946727 (Open Web Text)

Max Activating Token Index: 68

Text #4

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.3812. Min Act: -0.1700

Data Index: 5092623 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.3796. Min Act: -0.1700

Data Index: 152207 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.3253. Min Act: -0.1700

Data Index: 6734534 (Open Web Text)

Max Activating Token Index: 36

Text #7

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.3573. Min Act: -0.1700

Data Index: 5780797 (Open Web Text)

Max Activating Token Index: 841

Text #8

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.2877. Min Act: -0.1700

Data Index: 5003254 (Open Web Text)

Max Activating Token Index: 832

Text #9

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.3146. Min Act: -0.1700

Data Index: 52856 (Open Web Text)

Max Activating Token Index: 588

Text #10

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.2892. Min Act: -0.1700

Data Index: 7112648 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.3044. Min Act: -0.1700

Data Index: 1512244 (Open Web Text)

Max Activating Token Index: 926

Text #12

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.3054. Min Act: -0.1700

Data Index: 3784209 (Open Web Text)

Max Activating Token Index: 786

Text #13

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.2592. Min Act: -0.1700

Data Index: 4079834 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.2699. Min Act: -0.1700

Data Index: 6631484 (Open Web Text)

Max Activating Token Index: 297

Text #15

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.2731. Min Act: -0.1700

Data Index: 7625897 (Open Web Text)

Max Activating Token Index: 187

Text #16

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.2344. Min Act: -0.1700

Data Index: 490640 (Open Web Text)

Max Activating Token Index: 905

Text #17

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.2643. Min Act: -0.1700

Data Index: 5851692 (Open Web Text)

Max Activating Token Index: 263

Text #18

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.2462. Min Act: -0.1700

Data Index: 5599779 (Open Web Text)

Max Activating Token Index: 498

Text #19

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.2577. Min Act: -0.1700

Data Index: 2347168 (Open Web Text)

Max Activating Token Index: 766