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

Dataset: Open Web Text

Neuron 786 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: 2.3913. Min Range: -2.3913

Max Act: 2.3913. Min Act: -0.1700

Data Index: 3308368 (Open Web Text)

Max Activating Token Index: 229

Text #1

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.3807. Min Act: -0.1700

Data Index: 7061224 (Open Web Text)

Max Activating Token Index: 632

Text #2

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.3385. Min Act: -0.1700

Data Index: 6960403 (Open Web Text)

Max Activating Token Index: 993

Text #3

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2831. Min Act: -0.1700

Data Index: 488319 (Open Web Text)

Max Activating Token Index: 321

Text #4

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2780. Min Act: -0.1700

Data Index: 5773450 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2726. Min Act: -0.1700

Data Index: 657611 (Open Web Text)

Max Activating Token Index: 899

Text #6

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2549. Min Act: -0.1700

Data Index: 2898018 (Open Web Text)

Max Activating Token Index: 952

Text #7

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2743. Min Act: -0.1700

Data Index: 6047041 (Open Web Text)

Max Activating Token Index: 753

Text #8

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2632. Min Act: -0.1700

Data Index: 2605330 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2493. Min Act: -0.1700

Data Index: 7572729 (Open Web Text)

Max Activating Token Index: 946

Text #10

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2499. Min Act: -0.1700

Data Index: 7859075 (Open Web Text)

Max Activating Token Index: 303

Text #11

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2624. Min Act: -0.1700

Data Index: 5400067 (Open Web Text)

Max Activating Token Index: 892

Text #12

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2408. Min Act: -0.1700

Data Index: 3437029 (Open Web Text)

Max Activating Token Index: 775

Text #13

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2400. Min Act: -0.1700

Data Index: 1844041 (Open Web Text)

Max Activating Token Index: 821

Text #14

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2404. Min Act: -0.1700

Data Index: 7422278 (Open Web Text)

Max Activating Token Index: 181

Text #15

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2473. Min Act: -0.1700

Data Index: 995244 (Open Web Text)

Max Activating Token Index: 894

Text #16

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2357. Min Act: -0.1700

Data Index: 4822865 (Open Web Text)

Max Activating Token Index: 601

Text #17

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2343. Min Act: -0.1700

Data Index: 6029958 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2234. Min Act: -0.1700

Data Index: 5296850 (Open Web Text)

Max Activating Token Index: 655

Text #19

Max Range: 2.3913. Min Range: -2.3913

Max Act: 2.2288. Min Act: -0.1700

Data Index: 4142895 (Open Web Text)

Max Activating Token Index: 647