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

Dataset: Open Web Text

Neuron 10 in Layer 2

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: 1.6441. Min Range: -1.6441

Max Act: 1.6441. Min Act: -0.1700

Data Index: 4334059 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.6299. Min Act: -0.1700

Data Index: 5985885 (Open Web Text)

Max Activating Token Index: 473

Text #2

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.6267. Min Act: -0.1700

Data Index: 3991736 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.6075. Min Act: -0.1700

Data Index: 5520358 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.6000. Min Act: -0.1700

Data Index: 5058653 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5936. Min Act: -0.1700

Data Index: 3772327 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5957. Min Act: -0.1700

Data Index: 817083 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5925. Min Act: -0.1700

Data Index: 5795597 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5879. Min Act: -0.1700

Data Index: 4003332 (Open Web Text)

Max Activating Token Index: 137

Text #9

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5967. Min Act: -0.1700

Data Index: 2484124 (Open Web Text)

Max Activating Token Index: 120

Text #10

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5870. Min Act: -0.1700

Data Index: 8716108 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5843. Min Act: -0.1700

Data Index: 6057280 (Open Web Text)

Max Activating Token Index: 227

Text #12

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5809. Min Act: -0.1700

Data Index: 3176756 (Open Web Text)

Max Activating Token Index: 259

Text #13

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5812. Min Act: -0.1700

Data Index: 7608764 (Open Web Text)

Max Activating Token Index: 921

Text #14

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5861. Min Act: -0.1700

Data Index: 759518 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5782. Min Act: -0.1700

Data Index: 7282077 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5852. Min Act: -0.1700

Data Index: 8162006 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5770. Min Act: -0.1700

Data Index: 6869817 (Open Web Text)

Max Activating Token Index: 901

Text #18

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5719. Min Act: -0.1700

Data Index: 1573743 (Open Web Text)

Max Activating Token Index: 642

Text #19

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5720. Min Act: -0.1700

Data Index: 7814285 (Open Web Text)

Max Activating Token Index: 474