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

Dataset: Open Web Text

Neuron 2867 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: 2.8336. Min Range: -2.8336

Max Act: 2.8336. Min Act: -0.1700

Data Index: 4160396 (Open Web Text)

Max Activating Token Index: 876

Text #1

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7928. Min Act: -0.1700

Data Index: 2967853 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7736. Min Act: -0.1700

Data Index: 1233563 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7743. Min Act: -0.1700

Data Index: 2793963 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7623. Min Act: -0.1700

Data Index: 6086080 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7691. Min Act: -0.1700

Data Index: 6858797 (Open Web Text)

Max Activating Token Index: 935

Text #6

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7645. Min Act: -0.1700

Data Index: 3248723 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7488. Min Act: -0.1700

Data Index: 851707 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7253. Min Act: -0.1700

Data Index: 7800582 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7173. Min Act: -0.1700

Data Index: 5722892 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7076. Min Act: -0.1700

Data Index: 8306533 (Open Web Text)

Max Activating Token Index: 506

Text #11

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7017. Min Act: -0.1700

Data Index: 5371414 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7085. Min Act: -0.1700

Data Index: 7806572 (Open Web Text)

Max Activating Token Index: 760

Text #13

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.6976. Min Act: -0.1700

Data Index: 3481975 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.7009. Min Act: -0.1700

Data Index: 6217305 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.6854. Min Act: -0.1700

Data Index: 6288010 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.6985. Min Act: -0.1700

Data Index: 6632897 (Open Web Text)

Max Activating Token Index: 929

Text #17

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.6857. Min Act: -0.1700

Data Index: 2594290 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.6841. Min Act: -0.1700

Data Index: 4628383 (Open Web Text)

Max Activating Token Index: 933

Text #19

Max Range: 2.8336. Min Range: -2.8336

Max Act: 2.6942. Min Act: -0.1700

Data Index: 3244490 (Open Web Text)

Max Activating Token Index: 3