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

Dataset: Open Web Text

Neuron 2502 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: 3.0131. Min Range: -3.0131

Max Act: 3.0131. Min Act: -0.1700

Data Index: 3566526 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.9787. Min Act: -0.1700

Data Index: 4408154 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.9303. Min Act: -0.1700

Data Index: 6180004 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.9257. Min Act: -0.1700

Data Index: 608711 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.9052. Min Act: -0.1700

Data Index: 3322799 (Open Web Text)

Max Activating Token Index: 275

Text #5

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8828. Min Act: -0.1700

Data Index: 4057818 (Open Web Text)

Max Activating Token Index: 433

Text #6

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8769. Min Act: -0.1700

Data Index: 2904809 (Open Web Text)

Max Activating Token Index: 745

Text #7

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8881. Min Act: -0.1700

Data Index: 4312447 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8877. Min Act: -0.1700

Data Index: 6400142 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8562. Min Act: -0.1700

Data Index: 8819173 (Open Web Text)

Max Activating Token Index: 218

Text #10

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8677. Min Act: -0.1700

Data Index: 7490018 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8497. Min Act: -0.1700

Data Index: 8812472 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8518. Min Act: -0.1700

Data Index: 3382466 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8591. Min Act: -0.1700

Data Index: 7056247 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8497. Min Act: -0.1700

Data Index: 5732351 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8394. Min Act: -0.1700

Data Index: 7714754 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8345. Min Act: -0.1700

Data Index: 8018606 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8397. Min Act: -0.1700

Data Index: 6405145 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8428. Min Act: -0.1700

Data Index: 8303494 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 3.0131. Min Range: -3.0131

Max Act: 2.8485. Min Act: -0.1700

Data Index: 5165353 (Open Web Text)

Max Activating Token Index: 681