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

Dataset: Open Web Text

Neuron 2420 in Layer 4

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: 4.2116. Min Range: -4.2116

Max Act: 4.2116. Min Act: -0.1700

Data Index: 5370105 (Open Web Text)

Max Activating Token Index: 174

Text #1

Max Range: 4.2116. Min Range: -4.2116

Max Act: 4.0860. Min Act: -0.1700

Data Index: 6994301 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 4.2116. Min Range: -4.2116

Max Act: 4.0749. Min Act: -0.1700

Data Index: 7192756 (Open Web Text)

Max Activating Token Index: 476

Text #3

Max Range: 4.2116. Min Range: -4.2116

Max Act: 4.1157. Min Act: -0.1700

Data Index: 368825 (Open Web Text)

Max Activating Token Index: 854

Text #4

Max Range: 4.2116. Min Range: -4.2116

Max Act: 4.0027. Min Act: -0.1700

Data Index: 3657329 (Open Web Text)

Max Activating Token Index: 615

Text #5

Max Range: 4.2116. Min Range: -4.2116

Max Act: 4.0033. Min Act: -0.1700

Data Index: 847279 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9719. Min Act: -0.1700

Data Index: 1124099 (Open Web Text)

Max Activating Token Index: 884

Text #7

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9868. Min Act: -0.1700

Data Index: 4044200 (Open Web Text)

Max Activating Token Index: 722

Text #8

Max Range: 4.2116. Min Range: -4.2116

Max Act: 4.0588. Min Act: -0.1700

Data Index: 3569324 (Open Web Text)

Max Activating Token Index: 622

Text #9

Max Range: 4.2116. Min Range: -4.2116

Max Act: 4.0005. Min Act: -0.1700

Data Index: 3644317 (Open Web Text)

Max Activating Token Index: 420

Text #10

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9462. Min Act: -0.1700

Data Index: 5995980 (Open Web Text)

Max Activating Token Index: 99

Text #11

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9525. Min Act: -0.1700

Data Index: 1300355 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9819. Min Act: -0.1700

Data Index: 6675442 (Open Web Text)

Max Activating Token Index: 999

Text #13

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9249. Min Act: -0.1700

Data Index: 1637216 (Open Web Text)

Max Activating Token Index: 228

Text #14

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.8650. Min Act: -0.1700

Data Index: 8346546 (Open Web Text)

Max Activating Token Index: 548

Text #15

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9109. Min Act: -0.1700

Data Index: 7469241 (Open Web Text)

Max Activating Token Index: 327

Text #16

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9151. Min Act: -0.1700

Data Index: 4927671 (Open Web Text)

Max Activating Token Index: 575

Text #17

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.8895. Min Act: -0.1700

Data Index: 563378 (Open Web Text)

Max Activating Token Index: 410

Text #18

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9723. Min Act: -0.1700

Data Index: 4820118 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 4.2116. Min Range: -4.2116

Max Act: 3.9641. Min Act: -0.1700

Data Index: 319634 (Open Web Text)

Max Activating Token Index: 646