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

Dataset: Open Web Text

Neuron 1712 in Layer 1

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: 1.8443. Min Range: -1.8443

Max Act: 1.8443. Min Act: -0.1700

Data Index: 1239132 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.8277. Min Act: -0.1700

Data Index: 2349114 (Open Web Text)

Max Activating Token Index: 272

Text #2

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.8277. Min Act: -0.1700

Data Index: 2134506 (Open Web Text)

Max Activating Token Index: 103

Text #3

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.8245. Min Act: -0.1700

Data Index: 900147 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.8156. Min Act: -0.1700

Data Index: 2577854 (Open Web Text)

Max Activating Token Index: 131

Text #5

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7965. Min Act: -0.1700

Data Index: 4252814 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7783. Min Act: -0.1700

Data Index: 683963 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7830. Min Act: -0.1700

Data Index: 5108084 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7807. Min Act: -0.1700

Data Index: 7462918 (Open Web Text)

Max Activating Token Index: 626

Text #9

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7739. Min Act: -0.1700

Data Index: 2713521 (Open Web Text)

Max Activating Token Index: 38

Text #10

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7771. Min Act: -0.1700

Data Index: 3794839 (Open Web Text)

Max Activating Token Index: 316

Text #11

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7611. Min Act: -0.1700

Data Index: 6220666 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7481. Min Act: -0.1700

Data Index: 5328095 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7590. Min Act: -0.1700

Data Index: 159486 (Open Web Text)

Max Activating Token Index: 104

Text #14

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7565. Min Act: -0.1700

Data Index: 3451594 (Open Web Text)

Max Activating Token Index: 40

Text #15

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7503. Min Act: -0.1700

Data Index: 3603882 (Open Web Text)

Max Activating Token Index: 68

Text #16

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7470. Min Act: -0.1700

Data Index: 3751500 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7463. Min Act: -0.1700

Data Index: 1425060 (Open Web Text)

Max Activating Token Index: 963

Text #18

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7425. Min Act: -0.1700

Data Index: 2716387 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 1.8443. Min Range: -1.8443

Max Act: 1.7579. Min Act: -0.1699

Data Index: 5528582 (Open Web Text)

Max Activating Token Index: 482