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

Dataset: Open Web Text

Neuron 2372 in Layer 6

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: 5.4300. Min Range: -5.4300

Max Act: 5.4087. Min Act: -0.1700

Data Index: 1756494 (Open Web Text)

Max Activating Token Index: 563

Text #1

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.4300. Min Act: -0.1700

Data Index: 1728595 (Open Web Text)

Max Activating Token Index: 518

Text #2

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3661. Min Act: -0.1700

Data Index: 6174522 (Open Web Text)

Max Activating Token Index: 226

Text #3

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3581. Min Act: -0.1700

Data Index: 7875150 (Open Web Text)

Max Activating Token Index: 594

Text #4

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3908. Min Act: -0.1700

Data Index: 138272 (Open Web Text)

Max Activating Token Index: 970

Text #5

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3876. Min Act: -0.1700

Data Index: 7372070 (Open Web Text)

Max Activating Token Index: 911

Text #6

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3739. Min Act: -0.1700

Data Index: 7213287 (Open Web Text)

Max Activating Token Index: 723

Text #7

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3881. Min Act: -0.1700

Data Index: 6668814 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3777. Min Act: -0.1700

Data Index: 3669354 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3663. Min Act: -0.1700

Data Index: 6202576 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3606. Min Act: -0.1700

Data Index: 5812898 (Open Web Text)

Max Activating Token Index: 483

Text #11

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3556. Min Act: -0.1700

Data Index: 4578212 (Open Web Text)

Max Activating Token Index: 130

Text #12

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3454. Min Act: -0.1700

Data Index: 1757240 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3357. Min Act: -0.1700

Data Index: 6875640 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3570. Min Act: -0.1700

Data Index: 4190836 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3773. Min Act: -0.1700

Data Index: 2918307 (Open Web Text)

Max Activating Token Index: 816

Text #16

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3353. Min Act: -0.1700

Data Index: 6523672 (Open Web Text)

Max Activating Token Index: 299

Text #17

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3450. Min Act: -0.1700

Data Index: 1859256 (Open Web Text)

Max Activating Token Index: 673

Text #18

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3032. Min Act: -0.1700

Data Index: 759204 (Open Web Text)

Max Activating Token Index: 675

Text #19

Max Range: 5.4300. Min Range: -5.4300

Max Act: 5.3624. Min Act: -0.1700

Data Index: 249855 (Open Web Text)

Max Activating Token Index: 58