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

Dataset: Open Web Text

Neuron 274 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: 5.4652. Min Range: -5.4652

Max Act: 5.4652. Min Act: -0.1700

Data Index: 1804578 (Open Web Text)

Max Activating Token Index: 717

Text #1

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.4543. Min Act: -0.1700

Data Index: 2587616 (Open Web Text)

Max Activating Token Index: 405

Text #2

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.4458. Min Act: -0.1700

Data Index: 2084280 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.4585. Min Act: -0.1700

Data Index: 5169978 (Open Web Text)

Max Activating Token Index: 667

Text #4

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.4415. Min Act: -0.1700

Data Index: 5083061 (Open Web Text)

Max Activating Token Index: 841

Text #5

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.4424. Min Act: -0.1700

Data Index: 4697110 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3954. Min Act: -0.1700

Data Index: 1494387 (Open Web Text)

Max Activating Token Index: 493

Text #7

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.4231. Min Act: -0.1700

Data Index: 3554929 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.4194. Min Act: -0.1700

Data Index: 7357286 (Open Web Text)

Max Activating Token Index: 537

Text #9

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3917. Min Act: -0.1700

Data Index: 3976023 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3811. Min Act: -0.1700

Data Index: 3389918 (Open Web Text)

Max Activating Token Index: 628

Text #11

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3816. Min Act: -0.1700

Data Index: 1680362 (Open Web Text)

Max Activating Token Index: 614

Text #12

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.4045. Min Act: -0.1700

Data Index: 6830964 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3958. Min Act: -0.1700

Data Index: 6607688 (Open Web Text)

Max Activating Token Index: 267

Text #14

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3726. Min Act: -0.1700

Data Index: 6522068 (Open Web Text)

Max Activating Token Index: 141

Text #15

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3862. Min Act: -0.1700

Data Index: 3427738 (Open Web Text)

Max Activating Token Index: 507

Text #16

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3547. Min Act: -0.1700

Data Index: 2365670 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3360. Min Act: -0.1700

Data Index: 756878 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3568. Min Act: -0.1700

Data Index: 5113839 (Open Web Text)

Max Activating Token Index: 149

Text #19

Max Range: 5.4652. Min Range: -5.4652

Max Act: 5.3633. Min Act: -0.1700

Data Index: 2473589 (Open Web Text)

Max Activating Token Index: 409