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

Dataset: Open Web Text

Neuron 727 in Layer 1

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: 1.8516. Min Range: -1.8516

Max Act: 1.8516. Min Act: -0.1700

Data Index: 5009228 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.8119. Min Act: -0.1683

Data Index: 6822044 (Open Web Text)

Max Activating Token Index: 259

Text #2

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7968. Min Act: -0.1697

Data Index: 5733473 (Open Web Text)

Max Activating Token Index: 747

Text #3

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7975. Min Act: -0.1700

Data Index: 5446494 (Open Web Text)

Max Activating Token Index: 807

Text #4

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7918. Min Act: -0.1690

Data Index: 7992965 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7934. Min Act: -0.1576

Data Index: 6376435 (Open Web Text)

Max Activating Token Index: 268

Text #6

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7853. Min Act: -0.1651

Data Index: 2913771 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7833. Min Act: -0.1700

Data Index: 1666220 (Open Web Text)

Max Activating Token Index: 402

Text #8

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7765. Min Act: -0.1699

Data Index: 3676282 (Open Web Text)

Max Activating Token Index: 494

Text #9

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7713. Min Act: -0.1656

Data Index: 6376431 (Open Web Text)

Max Activating Token Index: 813

Text #10

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7769. Min Act: -0.1700

Data Index: 6849400 (Open Web Text)

Max Activating Token Index: 131

Text #11

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7670. Min Act: -0.1596

Data Index: 1917945 (Open Web Text)

Max Activating Token Index: 647

Text #12

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7700. Min Act: -0.1700

Data Index: 1886515 (Open Web Text)

Max Activating Token Index: 274

Text #13

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7723. Min Act: -0.1700

Data Index: 2846508 (Open Web Text)

Max Activating Token Index: 62

Text #14

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7711. Min Act: -0.1675

Data Index: 1917946 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7714. Min Act: -0.1699

Data Index: 507996 (Open Web Text)

Max Activating Token Index: 691

Text #16

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7632. Min Act: -0.1667

Data Index: 6742456 (Open Web Text)

Max Activating Token Index: 102

Text #17

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7703. Min Act: -0.1699

Data Index: 4455469 (Open Web Text)

Max Activating Token Index: 231

Text #18

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7663. Min Act: -0.1565

Data Index: 6296482 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7640. Min Act: -0.1700

Data Index: 1861866 (Open Web Text)

Max Activating Token Index: 620