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

Dataset: Open Web Text

Neuron 1852 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: 4.8507. Min Range: -4.8507

Max Act: 4.8507. Min Act: -0.1700

Data Index: 5359701 (Open Web Text)

Max Activating Token Index: 302

Text #1

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.8299. Min Act: -0.1700

Data Index: 2982099 (Open Web Text)

Max Activating Token Index: 717

Text #2

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.8279. Min Act: -0.1700

Data Index: 520461 (Open Web Text)

Max Activating Token Index: 820

Text #3

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.8267. Min Act: -0.1700

Data Index: 7857969 (Open Web Text)

Max Activating Token Index: 776

Text #4

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.8165. Min Act: -0.1700

Data Index: 8427553 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.5574. Min Act: -0.1700

Data Index: 1446010 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.5729. Min Act: -0.1700

Data Index: 203943 (Open Web Text)

Max Activating Token Index: 422

Text #7

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.5242. Min Act: -0.1700

Data Index: 6276807 (Open Web Text)

Max Activating Token Index: 761

Text #8

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.5251. Min Act: -0.1700

Data Index: 73741 (Open Web Text)

Max Activating Token Index: 956

Text #9

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.4884. Min Act: -0.1700

Data Index: 5028849 (Open Web Text)

Max Activating Token Index: 946

Text #10

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.4714. Min Act: -0.1700

Data Index: 6052402 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.4106. Min Act: -0.1700

Data Index: 8447654 (Open Web Text)

Max Activating Token Index: 836

Text #12

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.4635. Min Act: -0.1700

Data Index: 3745556 (Open Web Text)

Max Activating Token Index: 960

Text #13

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.4011. Min Act: -0.1700

Data Index: 1106306 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.4199. Min Act: -0.1700

Data Index: 7256131 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.3898. Min Act: -0.1700

Data Index: 3104902 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.3834. Min Act: -0.1700

Data Index: 5402129 (Open Web Text)

Max Activating Token Index: 878

Text #17

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.4139. Min Act: -0.1700

Data Index: 1483281 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.4015. Min Act: -0.1700

Data Index: 4408814 (Open Web Text)

Max Activating Token Index: 494

Text #19

Max Range: 4.8507. Min Range: -4.8507

Max Act: 4.3876. Min Act: -0.1700

Data Index: 992226 (Open Web Text)

Max Activating Token Index: 425