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

Dataset: Open Web Text

Neuron 868 in Layer 1

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: 1.5714. Min Range: -1.5714

Max Act: 1.5714. Min Act: -0.1700

Data Index: 2907302 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5537. Min Act: -0.1700

Data Index: 1430981 (Open Web Text)

Max Activating Token Index: 648

Text #2

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5457. Min Act: -0.1693

Data Index: 5510631 (Open Web Text)

Max Activating Token Index: 541

Text #3

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5439. Min Act: -0.1699

Data Index: 2173240 (Open Web Text)

Max Activating Token Index: 242

Text #4

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5303. Min Act: -0.1700

Data Index: 8610095 (Open Web Text)

Max Activating Token Index: 544

Text #5

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5178. Min Act: -0.1700

Data Index: 2240794 (Open Web Text)

Max Activating Token Index: 110

Text #6

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5071. Min Act: -0.1700

Data Index: 4991007 (Open Web Text)

Max Activating Token Index: 55

Text #7

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5011. Min Act: -0.1700

Data Index: 1948041 (Open Web Text)

Max Activating Token Index: 673

Text #8

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5009. Min Act: -0.1700

Data Index: 7138182 (Open Web Text)

Max Activating Token Index: 88

Text #9

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5013. Min Act: -0.1700

Data Index: 6935629 (Open Web Text)

Max Activating Token Index: 139

Text #10

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4919. Min Act: -0.1700

Data Index: 1871271 (Open Web Text)

Max Activating Token Index: 340

Text #11

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4819. Min Act: -0.1700

Data Index: 4000070 (Open Web Text)

Max Activating Token Index: 452

Text #12

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4817. Min Act: -0.1700

Data Index: 7858429 (Open Web Text)

Max Activating Token Index: 216

Text #13

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4874. Min Act: -0.1700

Data Index: 7420159 (Open Web Text)

Max Activating Token Index: 52

Text #14

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4813. Min Act: -0.1700

Data Index: 718255 (Open Web Text)

Max Activating Token Index: 402

Text #15

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4797. Min Act: -0.1700

Data Index: 5975084 (Open Web Text)

Max Activating Token Index: 298

Text #16

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4838. Min Act: -0.1700

Data Index: 2447198 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4915. Min Act: -0.1700

Data Index: 5868358 (Open Web Text)

Max Activating Token Index: 415

Text #18

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4828. Min Act: -0.1700

Data Index: 7161177 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.4773. Min Act: -0.1700

Data Index: 4881965 (Open Web Text)

Max Activating Token Index: 395