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

Dataset: Open Web Text

Neuron 2887 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: 4.1588. Min Range: -4.1588

Max Act: 4.1588. Min Act: -0.1700

Data Index: 2320156 (Open Web Text)

Max Activating Token Index: 54

Text #1

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0649. Min Act: -0.1700

Data Index: 5542760 (Open Web Text)

Max Activating Token Index: 692

Text #2

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0579. Min Act: -0.1700

Data Index: 2180646 (Open Web Text)

Max Activating Token Index: 352

Text #3

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0575. Min Act: -0.1700

Data Index: 216272 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0432. Min Act: -0.1700

Data Index: 2476031 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0624. Min Act: -0.1700

Data Index: 1792706 (Open Web Text)

Max Activating Token Index: 646

Text #6

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9812. Min Act: -0.1700

Data Index: 6925753 (Open Web Text)

Max Activating Token Index: 991

Text #7

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0060. Min Act: -0.1700

Data Index: 6825549 (Open Web Text)

Max Activating Token Index: 1017

Text #8

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0526. Min Act: -0.1700

Data Index: 1792705 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 4.1588. Min Range: -4.1588

Max Act: 4.0331. Min Act: -0.1700

Data Index: 1387950 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9387. Min Act: -0.1700

Data Index: 6430860 (Open Web Text)

Max Activating Token Index: 880

Text #11

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9968. Min Act: -0.1700

Data Index: 4092226 (Open Web Text)

Max Activating Token Index: 433

Text #12

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9853. Min Act: -0.1700

Data Index: 2704799 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9473. Min Act: -0.1700

Data Index: 1064617 (Open Web Text)

Max Activating Token Index: 967

Text #14

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9817. Min Act: -0.1700

Data Index: 5112562 (Open Web Text)

Max Activating Token Index: 431

Text #15

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9894. Min Act: -0.1700

Data Index: 4817637 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9809. Min Act: -0.1700

Data Index: 7934940 (Open Web Text)

Max Activating Token Index: 378

Text #17

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9703. Min Act: -0.1700

Data Index: 5992839 (Open Web Text)

Max Activating Token Index: 954

Text #18

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9446. Min Act: -0.1700

Data Index: 3938005 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 4.1588. Min Range: -4.1588

Max Act: 3.9411. Min Act: -0.1700

Data Index: 4632558 (Open Web Text)

Max Activating Token Index: 688