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

Dataset: Open Web Text

Neuron 2512 in Layer 6

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: 3.5218. Min Range: -3.5218

Max Act: 3.5218. Min Act: -0.1700

Data Index: 6212501 (Open Web Text)

Max Activating Token Index: 814

Text #1

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.4815. Min Act: -0.1700

Data Index: 7332365 (Open Web Text)

Max Activating Token Index: 282

Text #2

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.4328. Min Act: -0.1700

Data Index: 3164977 (Open Web Text)

Max Activating Token Index: 831

Text #3

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.4107. Min Act: -0.1700

Data Index: 6875447 (Open Web Text)

Max Activating Token Index: 763

Text #4

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3732. Min Act: -0.1700

Data Index: 3210473 (Open Web Text)

Max Activating Token Index: 575

Text #5

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3723. Min Act: -0.1700

Data Index: 3126208 (Open Web Text)

Max Activating Token Index: 852

Text #6

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3629. Min Act: -0.1700

Data Index: 5888698 (Open Web Text)

Max Activating Token Index: 123

Text #7

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3577. Min Act: -0.1700

Data Index: 2509177 (Open Web Text)

Max Activating Token Index: 341

Text #8

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3475. Min Act: -0.1700

Data Index: 1392772 (Open Web Text)

Max Activating Token Index: 700

Text #9

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3232. Min Act: -0.1700

Data Index: 2868705 (Open Web Text)

Max Activating Token Index: 432

Text #10

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.2940. Min Act: -0.1700

Data Index: 3826792 (Open Web Text)

Max Activating Token Index: 834

Text #11

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3175. Min Act: -0.1700

Data Index: 6240018 (Open Web Text)

Max Activating Token Index: 955

Text #12

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3236. Min Act: -0.1700

Data Index: 4944649 (Open Web Text)

Max Activating Token Index: 283

Text #13

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3179. Min Act: -0.1700

Data Index: 5401138 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.2948. Min Act: -0.1700

Data Index: 5170244 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3021. Min Act: -0.1700

Data Index: 2569570 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3068. Min Act: -0.1700

Data Index: 6722199 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3127. Min Act: -0.1700

Data Index: 5893642 (Open Web Text)

Max Activating Token Index: 921

Text #18

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.3149. Min Act: -0.1700

Data Index: 1476665 (Open Web Text)

Max Activating Token Index: 679

Text #19

Max Range: 3.5218. Min Range: -3.5218

Max Act: 3.2838. Min Act: -0.1700

Data Index: 8211558 (Open Web Text)

Max Activating Token Index: 915