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

Dataset: Open Web Text

Neuron 378 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: 2.8314. Min Range: -2.8314

Max Act: 2.8283. Min Act: -0.1700

Data Index: 3740415 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.8312. Min Act: -0.1700

Data Index: 5243175 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.8314. Min Act: -0.1700

Data Index: 294782 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.8280. Min Act: -0.1700

Data Index: 6991273 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.8283. Min Act: -0.1700

Data Index: 7257034 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.8128. Min Act: -0.1700

Data Index: 7488178 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7934. Min Act: -0.1700

Data Index: 6247630 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.8023. Min Act: -0.1700

Data Index: 7564024 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7913. Min Act: -0.1700

Data Index: 4244854 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7942. Min Act: -0.1700

Data Index: 6333235 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7809. Min Act: -0.1700

Data Index: 6599105 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7848. Min Act: -0.1700

Data Index: 692415 (Open Web Text)

Max Activating Token Index: 742

Text #12

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7843. Min Act: -0.1700

Data Index: 5933263 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7608. Min Act: -0.1700

Data Index: 2187306 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7686. Min Act: -0.1700

Data Index: 2202012 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7673. Min Act: -0.1700

Data Index: 1405596 (Open Web Text)

Max Activating Token Index: 480

Text #16

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7647. Min Act: -0.1700

Data Index: 5394362 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7637. Min Act: -0.1700

Data Index: 2266638 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7608. Min Act: -0.1700

Data Index: 2388249 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.8314. Min Range: -2.8314

Max Act: 2.7703. Min Act: -0.1700

Data Index: 3952818 (Open Web Text)

Max Activating Token Index: 4