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

Dataset: Open Web Text

Neuron 1520 in Layer 3

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: 4.4923. Min Range: -4.4923

Max Act: 4.4923. Min Act: -0.1700

Data Index: 717489 (Open Web Text)

Max Activating Token Index: 665

Text #1

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.4369. Min Act: -0.1700

Data Index: 2072738 (Open Web Text)

Max Activating Token Index: 217

Text #2

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.4085. Min Act: -0.1700

Data Index: 259774 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.4083. Min Act: -0.1700

Data Index: 918841 (Open Web Text)

Max Activating Token Index: 753

Text #4

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3904. Min Act: -0.1700

Data Index: 6210756 (Open Web Text)

Max Activating Token Index: 188

Text #5

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3800. Min Act: -0.1700

Data Index: 6659131 (Open Web Text)

Max Activating Token Index: 658

Text #6

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.4056. Min Act: -0.1700

Data Index: 7849068 (Open Web Text)

Max Activating Token Index: 315

Text #7

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3643. Min Act: -0.1700

Data Index: 513661 (Open Web Text)

Max Activating Token Index: 87

Text #8

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3330. Min Act: -0.1700

Data Index: 7685928 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3111. Min Act: -0.1700

Data Index: 673409 (Open Web Text)

Max Activating Token Index: 952

Text #10

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3533. Min Act: -0.1700

Data Index: 8204411 (Open Web Text)

Max Activating Token Index: 39

Text #11

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3634. Min Act: -0.1700

Data Index: 4760956 (Open Web Text)

Max Activating Token Index: 681

Text #12

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3010. Min Act: -0.1700

Data Index: 2037839 (Open Web Text)

Max Activating Token Index: 738

Text #13

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3021. Min Act: -0.1700

Data Index: 1227446 (Open Web Text)

Max Activating Token Index: 481

Text #14

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.2919. Min Act: -0.1700

Data Index: 8475420 (Open Web Text)

Max Activating Token Index: 968

Text #15

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.2705. Min Act: -0.1700

Data Index: 6028851 (Open Web Text)

Max Activating Token Index: 383

Text #16

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3489. Min Act: -0.1700

Data Index: 2031103 (Open Web Text)

Max Activating Token Index: 188

Text #17

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3040. Min Act: -0.1700

Data Index: 285488 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.3126. Min Act: -0.1700

Data Index: 6107347 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 4.4923. Min Range: -4.4923

Max Act: 4.2328. Min Act: -0.1700

Data Index: 3507601 (Open Web Text)

Max Activating Token Index: 559