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

Dataset: Open Web Text

Neuron 892 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: 2.6663. Min Range: -2.6663

Max Act: 2.6663. Min Act: -0.1700

Data Index: 3929906 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.6499. Min Act: -0.1700

Data Index: 5632439 (Open Web Text)

Max Activating Token Index: 731

Text #2

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.6211. Min Act: -0.1700

Data Index: 198522 (Open Web Text)

Max Activating Token Index: 298

Text #3

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.6197. Min Act: -0.1700

Data Index: 381536 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.6086. Min Act: -0.1700

Data Index: 4322326 (Open Web Text)

Max Activating Token Index: 180

Text #5

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5830. Min Act: -0.1700

Data Index: 4595438 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.6104. Min Act: -0.1700

Data Index: 4121249 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5953. Min Act: -0.1700

Data Index: 7361060 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5861. Min Act: -0.1700

Data Index: 3430602 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5781. Min Act: -0.1700

Data Index: 4377152 (Open Web Text)

Max Activating Token Index: 850

Text #10

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5834. Min Act: -0.1700

Data Index: 5849015 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5699. Min Act: -0.1700

Data Index: 6519692 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5712. Min Act: -0.1700

Data Index: 4068330 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5393. Min Act: -0.1700

Data Index: 5637397 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5642. Min Act: -0.1700

Data Index: 6748229 (Open Web Text)

Max Activating Token Index: 978

Text #15

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5607. Min Act: -0.1700

Data Index: 809733 (Open Web Text)

Max Activating Token Index: 951

Text #16

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5579. Min Act: -0.1700

Data Index: 8497796 (Open Web Text)

Max Activating Token Index: 905

Text #17

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5427. Min Act: -0.1700

Data Index: 1671192 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5477. Min Act: -0.1700

Data Index: 5137529 (Open Web Text)

Max Activating Token Index: 71

Text #19

Max Range: 2.6663. Min Range: -2.6663

Max Act: 2.5324. Min Act: -0.1700

Data Index: 1599898 (Open Web Text)

Max Activating Token Index: 298