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

Dataset: Open Web Text

Neuron 800 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: 5.5784. Min Range: -5.5784

Max Act: 5.5434. Min Act: -0.1700

Data Index: 5578543 (Open Web Text)

Max Activating Token Index: 376

Text #1

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.5784. Min Act: -0.1700

Data Index: 55555 (Open Web Text)

Max Activating Token Index: 410

Text #2

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.5042. Min Act: -0.1700

Data Index: 8723010 (Open Web Text)

Max Activating Token Index: 1000

Text #3

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.4583. Min Act: -0.1700

Data Index: 926592 (Open Web Text)

Max Activating Token Index: 841

Text #4

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.4811. Min Act: -0.1700

Data Index: 2150960 (Open Web Text)

Max Activating Token Index: 750

Text #5

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.4848. Min Act: -0.1700

Data Index: 3208859 (Open Web Text)

Max Activating Token Index: 478

Text #6

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.4233. Min Act: -0.1700

Data Index: 3300074 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.3900. Min Act: -0.1700

Data Index: 3432158 (Open Web Text)

Max Activating Token Index: 800

Text #8

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.4303. Min Act: -0.1700

Data Index: 3933157 (Open Web Text)

Max Activating Token Index: 202

Text #9

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.4124. Min Act: -0.1700

Data Index: 2929082 (Open Web Text)

Max Activating Token Index: 968

Text #10

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.3969. Min Act: -0.1700

Data Index: 3952654 (Open Web Text)

Max Activating Token Index: 324

Text #11

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.3838. Min Act: -0.1700

Data Index: 4728403 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.3324. Min Act: -0.1700

Data Index: 1840915 (Open Web Text)

Max Activating Token Index: 711

Text #13

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.3111. Min Act: -0.1700

Data Index: 8691063 (Open Web Text)

Max Activating Token Index: 387

Text #14

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.2942. Min Act: -0.1700

Data Index: 5794149 (Open Web Text)

Max Activating Token Index: 658

Text #15

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.2788. Min Act: -0.1700

Data Index: 923107 (Open Web Text)

Max Activating Token Index: 761

Text #16

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.2887. Min Act: -0.1700

Data Index: 139142 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.2881. Min Act: -0.1700

Data Index: 5464340 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.2750. Min Act: -0.1700

Data Index: 3544857 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.5784. Min Range: -5.5784

Max Act: 5.2649. Min Act: -0.1700

Data Index: 2919505 (Open Web Text)

Max Activating Token Index: 776