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

Dataset: Open Web Text

Neuron 1082 in Layer 3

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: 4.0354. Min Range: -4.0354

Max Act: 4.0354. Min Act: -0.1700

Data Index: 2713300 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.9540. Min Act: -0.1700

Data Index: 657771 (Open Web Text)

Max Activating Token Index: 98

Text #2

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.9373. Min Act: -0.1700

Data Index: 6717534 (Open Web Text)

Max Activating Token Index: 523

Text #3

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.8754. Min Act: -0.1700

Data Index: 3023346 (Open Web Text)

Max Activating Token Index: 601

Text #4

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.8083. Min Act: -0.1700

Data Index: 3150881 (Open Web Text)

Max Activating Token Index: 1019

Text #5

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7418. Min Act: -0.1700

Data Index: 3909077 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7617. Min Act: -0.1700

Data Index: 8497879 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7525. Min Act: -0.1700

Data Index: 5328298 (Open Web Text)

Max Activating Token Index: 192

Text #8

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7719. Min Act: -0.1700

Data Index: 5126281 (Open Web Text)

Max Activating Token Index: 314

Text #9

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7818. Min Act: -0.1700

Data Index: 6808729 (Open Web Text)

Max Activating Token Index: 632

Text #10

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7826. Min Act: -0.1700

Data Index: 1296889 (Open Web Text)

Max Activating Token Index: 285

Text #11

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7593. Min Act: -0.1700

Data Index: 3121719 (Open Web Text)

Max Activating Token Index: 212

Text #12

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7421. Min Act: -0.1700

Data Index: 7074468 (Open Web Text)

Max Activating Token Index: 838

Text #13

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7304. Min Act: -0.1700

Data Index: 6432904 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.6984. Min Act: -0.1700

Data Index: 4275333 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7433. Min Act: -0.1700

Data Index: 677211 (Open Web Text)

Max Activating Token Index: 719

Text #16

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.6923. Min Act: -0.1700

Data Index: 79 (Open Web Text)

Max Activating Token Index: 202

Text #17

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7028. Min Act: -0.1700

Data Index: 7096498 (Open Web Text)

Max Activating Token Index: 876

Text #18

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7144. Min Act: -0.1700

Data Index: 1605713 (Open Web Text)

Max Activating Token Index: 610

Text #19

Max Range: 4.0354. Min Range: -4.0354

Max Act: 3.7384. Min Act: -0.1700

Data Index: 2430986 (Open Web Text)

Max Activating Token Index: 900