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

Dataset: Open Web Text

Neuron 2738 in Layer 1

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: 1.5107. Min Range: -1.5107

Max Act: 1.5056. Min Act: -0.1688

Data Index: 6989620 (Open Web Text)

Max Activating Token Index: 1021

Text #1

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.5105. Min Act: -0.1699

Data Index: 2030872 (Open Web Text)

Max Activating Token Index: 683

Text #2

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.5004. Min Act: -0.1699

Data Index: 6556947 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4941. Min Act: -0.1700

Data Index: 8412682 (Open Web Text)

Max Activating Token Index: 680

Text #4

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.5107. Min Act: -0.1698

Data Index: 2822822 (Open Web Text)

Max Activating Token Index: 486

Text #5

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4991. Min Act: -0.1700

Data Index: 2402170 (Open Web Text)

Max Activating Token Index: 40

Text #6

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4957. Min Act: -0.1700

Data Index: 6682496 (Open Web Text)

Max Activating Token Index: 622

Text #7

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4929. Min Act: -0.1700

Data Index: 5491978 (Open Web Text)

Max Activating Token Index: 716

Text #8

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4920. Min Act: -0.1700

Data Index: 5135976 (Open Web Text)

Max Activating Token Index: 194

Text #9

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4873. Min Act: -0.1700

Data Index: 5096698 (Open Web Text)

Max Activating Token Index: 695

Text #10

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4906. Min Act: -0.1700

Data Index: 5445457 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4767. Min Act: -0.1700

Data Index: 3149465 (Open Web Text)

Max Activating Token Index: 34

Text #12

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4599. Min Act: -0.1689

Data Index: 8059179 (Open Web Text)

Max Activating Token Index: 676

Text #13

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4849. Min Act: -0.1700

Data Index: 7610098 (Open Web Text)

Max Activating Token Index: 666

Text #14

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4591. Min Act: -0.1700

Data Index: 5135013 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4796. Min Act: -0.1700

Data Index: 4712473 (Open Web Text)

Max Activating Token Index: 938

Text #16

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4741. Min Act: -0.1693

Data Index: 389719 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4634. Min Act: -0.1700

Data Index: 2318792 (Open Web Text)

Max Activating Token Index: 503

Text #18

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4707. Min Act: -0.1700

Data Index: 4414228 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.4648. Min Act: -0.1700

Data Index: 6082960 (Open Web Text)

Max Activating Token Index: 100