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

Dataset: Open Web Text

Neuron 2127 in Layer 0

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: 3.0580. Min Range: -3.0580

Max Act: 3.0580. Min Act: -0.1700

Data Index: 1749921 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 3.0580. Min Range: -3.0580

Max Act: 3.0410. Min Act: -0.1700

Data Index: 3215827 (Open Web Text)

Max Activating Token Index: 627

Text #2

Max Range: 3.0580. Min Range: -3.0580

Max Act: 3.0145. Min Act: -0.1700

Data Index: 292021 (Open Web Text)

Max Activating Token Index: 415

Text #3

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9860. Min Act: -0.1700

Data Index: 4066363 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9874. Min Act: -0.1700

Data Index: 647923 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9745. Min Act: -0.1700

Data Index: 8678211 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9691. Min Act: -0.1700

Data Index: 4270953 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9559. Min Act: -0.1700

Data Index: 292020 (Open Web Text)

Max Activating Token Index: 696

Text #8

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9550. Min Act: -0.1700

Data Index: 4940151 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9491. Min Act: -0.1700

Data Index: 6052974 (Open Web Text)

Max Activating Token Index: 342

Text #10

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9544. Min Act: -0.1700

Data Index: 856990 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9482. Min Act: -0.1700

Data Index: 4408550 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9490. Min Act: -0.1700

Data Index: 4596410 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9263. Min Act: -0.1700

Data Index: 1309569 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9360. Min Act: -0.1700

Data Index: 3345904 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9379. Min Act: -0.1700

Data Index: 708331 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9332. Min Act: -0.1700

Data Index: 5763831 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9130. Min Act: -0.1700

Data Index: 3028954 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9088. Min Act: -0.1700

Data Index: 4865923 (Open Web Text)

Max Activating Token Index: 823

Text #19

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9162. Min Act: -0.1700

Data Index: 1004526 (Open Web Text)

Max Activating Token Index: 66