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

Dataset: Open Web Text

Neuron 1453 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: 3.9905. Min Range: -3.9905

Max Act: 3.9905. Min Act: -0.1700

Data Index: 5377779 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.9798. Min Act: -0.1700

Data Index: 2748997 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.9018. Min Act: -0.1700

Data Index: 911668 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.9152. Min Act: -0.1700

Data Index: 4565469 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8873. Min Act: -0.1700

Data Index: 1444511 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8624. Min Act: -0.1700

Data Index: 6554405 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8487. Min Act: -0.1700

Data Index: 5086518 (Open Web Text)

Max Activating Token Index: 951

Text #7

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8540. Min Act: -0.1700

Data Index: 7967850 (Open Web Text)

Max Activating Token Index: 984

Text #8

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8421. Min Act: -0.1700

Data Index: 6669083 (Open Web Text)

Max Activating Token Index: 861

Text #9

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8430. Min Act: -0.1700

Data Index: 6189253 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8166. Min Act: -0.1700

Data Index: 6076172 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8152. Min Act: -0.1700

Data Index: 1500805 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8042. Min Act: -0.1700

Data Index: 3674059 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8151. Min Act: -0.1700

Data Index: 7728977 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8126. Min Act: -0.1700

Data Index: 7846022 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.8056. Min Act: -0.1700

Data Index: 5760582 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7567. Min Act: -0.1700

Data Index: 7462800 (Open Web Text)

Max Activating Token Index: 977

Text #17

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7554. Min Act: -0.1700

Data Index: 2229198 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7735. Min Act: -0.1700

Data Index: 875570 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.9905. Min Range: -3.9905

Max Act: 3.7753. Min Act: -0.1700

Data Index: 616978 (Open Web Text)

Max Activating Token Index: 3