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

Dataset: Open Web Text

Neuron 2523 in Layer 4

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: 5.0566. Min Range: -5.0566

Max Act: 5.0566. Min Act: -0.1700

Data Index: 237851 (Open Web Text)

Max Activating Token Index: 135

Text #1

Max Range: 5.0566. Min Range: -5.0566

Max Act: 5.0145. Min Act: -0.1700

Data Index: 3253846 (Open Web Text)

Max Activating Token Index: 741

Text #2

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9532. Min Act: -0.1700

Data Index: 146032 (Open Web Text)

Max Activating Token Index: 133

Text #3

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.7812. Min Act: -0.1700

Data Index: 2662162 (Open Web Text)

Max Activating Token Index: 675

Text #4

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.7488. Min Act: -0.1700

Data Index: 459637 (Open Web Text)

Max Activating Token Index: 477

Text #5

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.7262. Min Act: -0.1700

Data Index: 7248384 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.6760. Min Act: -0.1700

Data Index: 319635 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.6392. Min Act: -0.1700

Data Index: 8297838 (Open Web Text)

Max Activating Token Index: 939

Text #8

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.6263. Min Act: -0.1700

Data Index: 6441513 (Open Web Text)

Max Activating Token Index: 708

Text #9

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.6273. Min Act: -0.1700

Data Index: 6549705 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.6470. Min Act: -0.1700

Data Index: 347344 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.5976. Min Act: -0.1700

Data Index: 7974491 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.6317. Min Act: -0.1700

Data Index: 4142809 (Open Web Text)

Max Activating Token Index: 657

Text #13

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.6066. Min Act: -0.1700

Data Index: 7447877 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.5938. Min Act: -0.1700

Data Index: 4828152 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.5589. Min Act: -0.1700

Data Index: 2667575 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.5864. Min Act: -0.1700

Data Index: 5487095 (Open Web Text)

Max Activating Token Index: 591

Text #17

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.6065. Min Act: -0.1700

Data Index: 8069871 (Open Web Text)

Max Activating Token Index: 454

Text #18

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.6097. Min Act: -0.1700

Data Index: 8121935 (Open Web Text)

Max Activating Token Index: 503

Text #19

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.5853. Min Act: -0.1700

Data Index: 3965797 (Open Web Text)

Max Activating Token Index: 318