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

Dataset: Open Web Text

Neuron 2754 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: 6.4742. Min Range: -6.4742

Max Act: 6.4742. Min Act: -0.1700

Data Index: 3699474 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3887. Min Act: -0.1700

Data Index: 4396485 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3603. Min Act: -0.1700

Data Index: 8096070 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3333. Min Act: -0.1700

Data Index: 2099452 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3679. Min Act: -0.1700

Data Index: 12620 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3552. Min Act: -0.1700

Data Index: 4395858 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3499. Min Act: -0.1700

Data Index: 8461748 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3423. Min Act: -0.1700

Data Index: 8147454 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3202. Min Act: -0.1699

Data Index: 7212049 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3101. Min Act: -0.1700

Data Index: 1004904 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3050. Min Act: -0.1700

Data Index: 7531706 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3106. Min Act: -0.1700

Data Index: 7845645 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.2656. Min Act: -0.1700

Data Index: 7560571 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.3055. Min Act: -0.1700

Data Index: 2457293 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.2736. Min Act: -0.1700

Data Index: 2269116 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.2692. Min Act: -0.1700

Data Index: 1711160 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.2951. Min Act: -0.1700

Data Index: 1567664 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.2729. Min Act: -0.1700

Data Index: 594275 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.2850. Min Act: -0.1700

Data Index: 1228471 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 6.4742. Min Range: -6.4742

Max Act: 6.2569. Min Act: -0.1700

Data Index: 1073764 (Open Web Text)

Max Activating Token Index: 6