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

Dataset: Open Web Text

Neuron 3028 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: 4.3846. Min Range: -4.3846

Max Act: 4.3709. Min Act: -0.1700

Data Index: 7187231 (Open Web Text)

Max Activating Token Index: 563

Text #1

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.3663. Min Act: -0.1700

Data Index: 6484342 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.3846. Min Act: -0.1700

Data Index: 5070836 (Open Web Text)

Max Activating Token Index: 686

Text #3

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.3562. Min Act: -0.1700

Data Index: 6755322 (Open Web Text)

Max Activating Token Index: 608

Text #4

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.3136. Min Act: -0.1700

Data Index: 4481985 (Open Web Text)

Max Activating Token Index: 898

Text #5

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.3190. Min Act: -0.1700

Data Index: 3532957 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.3232. Min Act: -0.1700

Data Index: 1897990 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2966. Min Act: -0.1700

Data Index: 1358533 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2901. Min Act: -0.1700

Data Index: 3765410 (Open Web Text)

Max Activating Token Index: 763

Text #9

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2791. Min Act: -0.1700

Data Index: 4934426 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2795. Min Act: -0.1700

Data Index: 1737322 (Open Web Text)

Max Activating Token Index: 101

Text #11

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2876. Min Act: -0.1700

Data Index: 7300791 (Open Web Text)

Max Activating Token Index: 102

Text #12

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2986. Min Act: -0.1700

Data Index: 4917370 (Open Web Text)

Max Activating Token Index: 334

Text #13

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2937. Min Act: -0.1700

Data Index: 2872275 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2518. Min Act: -0.1700

Data Index: 1839922 (Open Web Text)

Max Activating Token Index: 903

Text #15

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2567. Min Act: -0.1700

Data Index: 3167313 (Open Web Text)

Max Activating Token Index: 899

Text #16

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2691. Min Act: -0.1700

Data Index: 5872443 (Open Web Text)

Max Activating Token Index: 708

Text #17

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2722. Min Act: -0.1700

Data Index: 6026881 (Open Web Text)

Max Activating Token Index: 458

Text #18

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2726. Min Act: -0.1700

Data Index: 4205215 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 4.3846. Min Range: -4.3846

Max Act: 4.2772. Min Act: -0.1700

Data Index: 6336258 (Open Web Text)

Max Activating Token Index: 574