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

Dataset: Open Web Text

Neuron 630 in Layer 5

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: 3.1182. Min Range: -3.1182

Max Act: 3.1182. Min Act: -0.1700

Data Index: 202643 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.1021. Min Act: -0.1700

Data Index: 1589622 (Open Web Text)

Max Activating Token Index: 325

Text #2

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.1062. Min Act: -0.1700

Data Index: 133048 (Open Web Text)

Max Activating Token Index: 50

Text #3

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0827. Min Act: -0.1700

Data Index: 4045960 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0768. Min Act: -0.1700

Data Index: 8139932 (Open Web Text)

Max Activating Token Index: 444

Text #5

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0990. Min Act: -0.1700

Data Index: 6275628 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0739. Min Act: -0.1700

Data Index: 3872583 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0771. Min Act: -0.1700

Data Index: 636070 (Open Web Text)

Max Activating Token Index: 827

Text #8

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0614. Min Act: -0.1700

Data Index: 5874781 (Open Web Text)

Max Activating Token Index: 298

Text #9

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0697. Min Act: -0.1700

Data Index: 4281144 (Open Web Text)

Max Activating Token Index: 971

Text #10

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0846. Min Act: -0.1700

Data Index: 8256581 (Open Web Text)

Max Activating Token Index: 934

Text #11

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0605. Min Act: -0.1700

Data Index: 5787603 (Open Web Text)

Max Activating Token Index: 538

Text #12

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0656. Min Act: -0.1700

Data Index: 6937826 (Open Web Text)

Max Activating Token Index: 386

Text #13

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0472. Min Act: -0.1700

Data Index: 4758217 (Open Web Text)

Max Activating Token Index: 795

Text #14

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0655. Min Act: -0.1700

Data Index: 8491815 (Open Web Text)

Max Activating Token Index: 401

Text #15

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0620. Min Act: -0.1700

Data Index: 4973208 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0542. Min Act: -0.1700

Data Index: 7119066 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0672. Min Act: -0.1700

Data Index: 1035186 (Open Web Text)

Max Activating Token Index: 879

Text #18

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0598. Min Act: -0.1700

Data Index: 5331505 (Open Web Text)

Max Activating Token Index: 106

Text #19

Max Range: 3.1182. Min Range: -3.1182

Max Act: 3.0532. Min Act: -0.1700

Data Index: 5740279 (Open Web Text)

Max Activating Token Index: 842