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

Dataset: Open Web Text

Neuron 2826 in Layer 6

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: 4.4582. Min Range: -4.4582

Max Act: 4.4582. Min Act: -0.1700

Data Index: 387061 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.3028. Min Act: -0.1700

Data Index: 3075798 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.2560. Min Act: -0.1700

Data Index: 6984295 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.2539. Min Act: -0.1700

Data Index: 6502275 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.2594. Min Act: -0.1700

Data Index: 2813406 (Open Web Text)

Max Activating Token Index: 678

Text #5

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.2731. Min Act: -0.1700

Data Index: 615758 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.2102. Min Act: -0.1700

Data Index: 5772397 (Open Web Text)

Max Activating Token Index: 74

Text #7

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.2005. Min Act: -0.1700

Data Index: 609525 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1996. Min Act: -0.1700

Data Index: 4710803 (Open Web Text)

Max Activating Token Index: 976

Text #9

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1664. Min Act: -0.1700

Data Index: 6453022 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1942. Min Act: -0.1700

Data Index: 8049025 (Open Web Text)

Max Activating Token Index: 227

Text #11

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1868. Min Act: -0.1700

Data Index: 4309392 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1965. Min Act: -0.1700

Data Index: 4507429 (Open Web Text)

Max Activating Token Index: 926

Text #13

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1405. Min Act: -0.1700

Data Index: 3973652 (Open Web Text)

Max Activating Token Index: 857

Text #14

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1587. Min Act: -0.1700

Data Index: 5723336 (Open Web Text)

Max Activating Token Index: 231

Text #15

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1683. Min Act: -0.1700

Data Index: 4531073 (Open Web Text)

Max Activating Token Index: 639

Text #16

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1562. Min Act: -0.1700

Data Index: 4138344 (Open Web Text)

Max Activating Token Index: 743

Text #17

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1829. Min Act: -0.1700

Data Index: 4201432 (Open Web Text)

Max Activating Token Index: 986

Text #18

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1514. Min Act: -0.1700

Data Index: 812280 (Open Web Text)

Max Activating Token Index: 924

Text #19

Max Range: 4.4582. Min Range: -4.4582

Max Act: 4.1683. Min Act: -0.1700

Data Index: 4389532 (Open Web Text)

Max Activating Token Index: 106