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

Dataset: Open Web Text

Neuron 2718 in Layer 5

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: 3.3581. Min Range: -3.3581

Max Act: 3.3377. Min Act: -0.1700

Data Index: 1236156 (Open Web Text)

Max Activating Token Index: 232

Text #1

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.3581. Min Act: -0.1700

Data Index: 3673442 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.2925. Min Act: -0.1700

Data Index: 1345059 (Open Web Text)

Max Activating Token Index: 570

Text #3

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.2260. Min Act: -0.1700

Data Index: 4361657 (Open Web Text)

Max Activating Token Index: 210

Text #4

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.2156. Min Act: -0.1700

Data Index: 7785186 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.1528. Min Act: -0.1700

Data Index: 1350153 (Open Web Text)

Max Activating Token Index: 723

Text #6

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.1399. Min Act: -0.1700

Data Index: 3841427 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.1376. Min Act: -0.1700

Data Index: 6077905 (Open Web Text)

Max Activating Token Index: 760

Text #8

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.1079. Min Act: -0.1700

Data Index: 3840723 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0970. Min Act: -0.1700

Data Index: 2662652 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0908. Min Act: -0.1700

Data Index: 3957566 (Open Web Text)

Max Activating Token Index: 707

Text #11

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0750. Min Act: -0.1700

Data Index: 8171523 (Open Web Text)

Max Activating Token Index: 310

Text #12

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0961. Min Act: -0.1700

Data Index: 8355695 (Open Web Text)

Max Activating Token Index: 917

Text #13

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0824. Min Act: -0.1700

Data Index: 5572660 (Open Web Text)

Max Activating Token Index: 914

Text #14

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0931. Min Act: -0.1700

Data Index: 232152 (Open Web Text)

Max Activating Token Index: 662

Text #15

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0551. Min Act: -0.1700

Data Index: 2786560 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0823. Min Act: -0.1700

Data Index: 2226919 (Open Web Text)

Max Activating Token Index: 846

Text #17

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.1016. Min Act: -0.1700

Data Index: 8414573 (Open Web Text)

Max Activating Token Index: 545

Text #18

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0595. Min Act: -0.1700

Data Index: 1599913 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 3.3581. Min Range: -3.3581

Max Act: 3.0591. Min Act: -0.1700

Data Index: 666946 (Open Web Text)

Max Activating Token Index: 473