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

Dataset: Open Web Text

Neuron 1927 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: 3.2521. Min Range: -3.2521

Max Act: 3.2521. Min Act: -0.1700

Data Index: 3721393 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.2390. Min Act: -0.1700

Data Index: 2933691 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.2357. Min Act: -0.1700

Data Index: 4463926 (Open Web Text)

Max Activating Token Index: 857

Text #3

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.2233. Min Act: -0.1700

Data Index: 5071011 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.2060. Min Act: -0.1700

Data Index: 3874462 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1991. Min Act: -0.1700

Data Index: 3284536 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.2054. Min Act: -0.1700

Data Index: 6408364 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.2012. Min Act: -0.1700

Data Index: 3832646 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1611. Min Act: -0.1700

Data Index: 7282288 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1624. Min Act: -0.1700

Data Index: 7779134 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1592. Min Act: -0.1700

Data Index: 1607102 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1542. Min Act: -0.1700

Data Index: 3654891 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1414. Min Act: -0.1700

Data Index: 5635248 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1356. Min Act: -0.1700

Data Index: 2172606 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1356. Min Act: -0.1700

Data Index: 6038013 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1299. Min Act: -0.1700

Data Index: 3007112 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1371. Min Act: -0.1700

Data Index: 2568674 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1493. Min Act: -0.1700

Data Index: 8442492 (Open Web Text)

Max Activating Token Index: 535

Text #18

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1412. Min Act: -0.1700

Data Index: 953900 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.2521. Min Range: -3.2521

Max Act: 3.1403. Min Act: -0.1700

Data Index: 1205757 (Open Web Text)

Max Activating Token Index: 977