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

Dataset: Open Web Text

Neuron 947 in Layer 4

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: 3.2935. Min Range: -3.2935

Max Act: 3.2935. Min Act: -0.1700

Data Index: 3092070 (Open Web Text)

Max Activating Token Index: 891

Text #1

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.2577. Min Act: -0.1700

Data Index: 1685473 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.2429. Min Act: -0.1700

Data Index: 659548 (Open Web Text)

Max Activating Token Index: 378

Text #3

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.2398. Min Act: -0.1700

Data Index: 7766814 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.2433. Min Act: -0.1700

Data Index: 3634151 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.2276. Min Act: -0.1700

Data Index: 7751258 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.2365. Min Act: -0.1700

Data Index: 303020 (Open Web Text)

Max Activating Token Index: 710

Text #7

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.2297. Min Act: -0.1700

Data Index: 2402934 (Open Web Text)

Max Activating Token Index: 671

Text #8

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1570. Min Act: -0.1700

Data Index: 6229312 (Open Web Text)

Max Activating Token Index: 841

Text #9

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1745. Min Act: -0.1700

Data Index: 5747618 (Open Web Text)

Max Activating Token Index: 95

Text #10

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1988. Min Act: -0.1700

Data Index: 3188589 (Open Web Text)

Max Activating Token Index: 351

Text #11

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1937. Min Act: -0.1700

Data Index: 5158703 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1658. Min Act: -0.1700

Data Index: 729598 (Open Web Text)

Max Activating Token Index: 995

Text #13

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1022. Min Act: -0.1700

Data Index: 8560527 (Open Web Text)

Max Activating Token Index: 154

Text #14

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1692. Min Act: -0.1700

Data Index: 5601635 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1692. Min Act: -0.1700

Data Index: 489087 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1647. Min Act: -0.1700

Data Index: 3676664 (Open Web Text)

Max Activating Token Index: 248

Text #17

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1823. Min Act: -0.1700

Data Index: 4751496 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1659. Min Act: -0.1700

Data Index: 2466010 (Open Web Text)

Max Activating Token Index: 650

Text #19

Max Range: 3.2935. Min Range: -3.2935

Max Act: 3.1127. Min Act: -0.1700

Data Index: 5278560 (Open Web Text)

Max Activating Token Index: 596