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

Dataset: Open Web Text

Neuron 1513 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: 3.8327. Min Range: -3.8327

Max Act: 3.8327. Min Act: -0.1700

Data Index: 803131 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7460. Min Act: -0.1700

Data Index: 800023 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7560. Min Act: -0.1699

Data Index: 557153 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7363. Min Act: -0.1700

Data Index: 7844761 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7306. Min Act: -0.1700

Data Index: 5399127 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7320. Min Act: -0.1700

Data Index: 4547932 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7175. Min Act: -0.1700

Data Index: 4513683 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7175. Min Act: -0.1700

Data Index: 1666473 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7175. Min Act: -0.1700

Data Index: 12953 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7328. Min Act: -0.1700

Data Index: 3878492 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7175. Min Act: -0.1700

Data Index: 432057 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7371. Min Act: -0.1700

Data Index: 8334388 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7242. Min Act: -0.1700

Data Index: 6681430 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.6909. Min Act: -0.1700

Data Index: 697795 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.6737. Min Act: -0.1700

Data Index: 681847 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.6909. Min Act: -0.1700

Data Index: 4121364 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.6950. Min Act: -0.1700

Data Index: 191659 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.6757. Min Act: -0.1700

Data Index: 3766217 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7013. Min Act: -0.1700

Data Index: 1188742 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.8327. Min Range: -3.8327

Max Act: 3.7056. Min Act: -0.1700

Data Index: 5024944 (Open Web Text)

Max Activating Token Index: 4