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

Dataset: Open Web Text

Neuron 3036 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: 3.6834. Min Range: -3.6834

Max Act: 3.6834. Min Act: -0.1700

Data Index: 6816156 (Open Web Text)

Max Activating Token Index: 697

Text #1

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.6480. Min Act: -0.1700

Data Index: 7413661 (Open Web Text)

Max Activating Token Index: 129

Text #2

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5818. Min Act: -0.1700

Data Index: 8199247 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5812. Min Act: -0.1700

Data Index: 6872652 (Open Web Text)

Max Activating Token Index: 497

Text #4

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5537. Min Act: -0.1700

Data Index: 7950972 (Open Web Text)

Max Activating Token Index: 674

Text #5

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5358. Min Act: -0.1700

Data Index: 8081429 (Open Web Text)

Max Activating Token Index: 727

Text #6

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5601. Min Act: -0.1700

Data Index: 320647 (Open Web Text)

Max Activating Token Index: 803

Text #7

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5128. Min Act: -0.1700

Data Index: 7413660 (Open Web Text)

Max Activating Token Index: 625

Text #8

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5255. Min Act: -0.1700

Data Index: 8081427 (Open Web Text)

Max Activating Token Index: 923

Text #9

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5109. Min Act: -0.1700

Data Index: 5052791 (Open Web Text)

Max Activating Token Index: 900

Text #10

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4862. Min Act: -0.1700

Data Index: 7925331 (Open Web Text)

Max Activating Token Index: 1005

Text #11

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5175. Min Act: -0.1700

Data Index: 5542370 (Open Web Text)

Max Activating Token Index: 755

Text #12

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4843. Min Act: -0.1700

Data Index: 7061788 (Open Web Text)

Max Activating Token Index: 793

Text #13

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4820. Min Act: -0.1700

Data Index: 5921658 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4952. Min Act: -0.1700

Data Index: 7404548 (Open Web Text)

Max Activating Token Index: 775

Text #15

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4732. Min Act: -0.1700

Data Index: 7199010 (Open Web Text)

Max Activating Token Index: 506

Text #16

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4663. Min Act: -0.1700

Data Index: 8081422 (Open Web Text)

Max Activating Token Index: 868

Text #17

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4614. Min Act: -0.1700

Data Index: 4752335 (Open Web Text)

Max Activating Token Index: 990

Text #18

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4673. Min Act: -0.1700

Data Index: 5766260 (Open Web Text)

Max Activating Token Index: 503

Text #19

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4573. Min Act: -0.1700

Data Index: 2765215 (Open Web Text)

Max Activating Token Index: 518