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

Dataset: Open Web Text

Neuron 1903 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: 4.6901. Min Range: -4.6901

Max Act: 4.6901. Min Act: -0.1700

Data Index: 7751393 (Open Web Text)

Max Activating Token Index: 773

Text #1

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.5049. Min Act: -0.1700

Data Index: 891253 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.4175. Min Act: -0.1700

Data Index: 4949460 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.4419. Min Act: -0.1700

Data Index: 7384007 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.4329. Min Act: -0.1700

Data Index: 5194638 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.4143. Min Act: -0.1700

Data Index: 3425188 (Open Web Text)

Max Activating Token Index: 720

Text #6

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3892. Min Act: -0.1700

Data Index: 4677839 (Open Web Text)

Max Activating Token Index: 355

Text #7

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3833. Min Act: -0.1700

Data Index: 996220 (Open Web Text)

Max Activating Token Index: 766

Text #8

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3789. Min Act: -0.1700

Data Index: 4426621 (Open Web Text)

Max Activating Token Index: 1010

Text #9

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3957. Min Act: -0.1700

Data Index: 832935 (Open Web Text)

Max Activating Token Index: 695

Text #10

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3884. Min Act: -0.1700

Data Index: 532794 (Open Web Text)

Max Activating Token Index: 872

Text #11

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3951. Min Act: -0.1700

Data Index: 7123147 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3479. Min Act: -0.1699

Data Index: 7430477 (Open Web Text)

Max Activating Token Index: 711

Text #13

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3477. Min Act: -0.1700

Data Index: 7683934 (Open Web Text)

Max Activating Token Index: 190

Text #14

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3642. Min Act: -0.1700

Data Index: 5478933 (Open Web Text)

Max Activating Token Index: 608

Text #15

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3645. Min Act: -0.1700

Data Index: 1595827 (Open Web Text)

Max Activating Token Index: 422

Text #16

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3552. Min Act: -0.1700

Data Index: 4159124 (Open Web Text)

Max Activating Token Index: 820

Text #17

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3724. Min Act: -0.1700

Data Index: 4868895 (Open Web Text)

Max Activating Token Index: 727

Text #18

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3487. Min Act: -0.1700

Data Index: 7995861 (Open Web Text)

Max Activating Token Index: 914

Text #19

Max Range: 4.6901. Min Range: -4.6901

Max Act: 4.3237. Min Act: -0.1700

Data Index: 3057660 (Open Web Text)

Max Activating Token Index: 539