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

Dataset: Open Web Text

Neuron 1452 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: 4.6805. Min Range: -4.6805

Max Act: 4.6805. Min Act: -0.1700

Data Index: 4650028 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.5419. Min Act: -0.1700

Data Index: 4708624 (Open Web Text)

Max Activating Token Index: 302

Text #2

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4901. Min Act: -0.1700

Data Index: 6713587 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4739. Min Act: -0.1700

Data Index: 4538678 (Open Web Text)

Max Activating Token Index: 785

Text #4

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.5045. Min Act: -0.1700

Data Index: 4299730 (Open Web Text)

Max Activating Token Index: 205

Text #5

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4799. Min Act: -0.1700

Data Index: 4277687 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4982. Min Act: -0.1700

Data Index: 5723223 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4210. Min Act: -0.1699

Data Index: 1420631 (Open Web Text)

Max Activating Token Index: 389

Text #8

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4791. Min Act: -0.1700

Data Index: 253337 (Open Web Text)

Max Activating Token Index: 267

Text #9

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4749. Min Act: -0.1700

Data Index: 6711562 (Open Web Text)

Max Activating Token Index: 721

Text #10

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4265. Min Act: -0.1700

Data Index: 2501387 (Open Web Text)

Max Activating Token Index: 475

Text #11

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4740. Min Act: -0.1700

Data Index: 4184842 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4972. Min Act: -0.1700

Data Index: 5339869 (Open Web Text)

Max Activating Token Index: 455

Text #13

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4538. Min Act: -0.1700

Data Index: 825035 (Open Web Text)

Max Activating Token Index: 693

Text #14

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4709. Min Act: -0.1700

Data Index: 7103999 (Open Web Text)

Max Activating Token Index: 593

Text #15

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4887. Min Act: -0.1700

Data Index: 1119075 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4527. Min Act: -0.1700

Data Index: 1140359 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4745. Min Act: -0.1700

Data Index: 1708916 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4994. Min Act: -0.1700

Data Index: 4967073 (Open Web Text)

Max Activating Token Index: 239

Text #19

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4779. Min Act: -0.1700

Data Index: 2520038 (Open Web Text)

Max Activating Token Index: 319