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

Dataset: Open Web Text

Neuron 1096 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: 1.8709. Min Range: -1.8709

Max Act: 1.8709. Min Act: -0.1700

Data Index: 3244813 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6969. Min Act: -0.1696

Data Index: 6886278 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6890. Min Act: -0.1694

Data Index: 141420 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6705. Min Act: -0.1512

Data Index: 8412446 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6645. Min Act: -0.1699

Data Index: 6316206 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6549. Min Act: -0.1700

Data Index: 7493972 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6496. Min Act: -0.1560

Data Index: 4020807 (Open Web Text)

Max Activating Token Index: 883

Text #7

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6461. Min Act: -0.1688

Data Index: 4133549 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6431. Min Act: -0.1696

Data Index: 2510089 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6411. Min Act: -0.1698

Data Index: 7558230 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6469. Min Act: -0.1669

Data Index: 4664027 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6468. Min Act: -0.1698

Data Index: 1733849 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6292. Min Act: -0.1629

Data Index: 3056825 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6163. Min Act: -0.1585

Data Index: 1320892 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6272. Min Act: -0.1681

Data Index: 3479731 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6290. Min Act: -0.1698

Data Index: 1284956 (Open Web Text)

Max Activating Token Index: 814

Text #16

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6265. Min Act: -0.1685

Data Index: 2688922 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6075. Min Act: -0.1698

Data Index: 4844629 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6132. Min Act: -0.1697

Data Index: 7779455 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 1.8709. Min Range: -1.8709

Max Act: 1.6103. Min Act: -0.1605

Data Index: 6712734 (Open Web Text)

Max Activating Token Index: 4