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

Dataset: Open Web Text

Neuron 1815 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: 3.0899. Min Range: -3.0899

Max Act: 3.0899. Min Act: -0.1700

Data Index: 7812578 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0720. Min Act: -0.1700

Data Index: 7733900 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0671. Min Act: -0.1700

Data Index: 2047183 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0571. Min Act: -0.1700

Data Index: 3551435 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0585. Min Act: -0.1700

Data Index: 5908276 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0501. Min Act: -0.1700

Data Index: 5944167 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0454. Min Act: -0.1700

Data Index: 5040721 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0357. Min Act: -0.1700

Data Index: 5421306 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0335. Min Act: -0.1700

Data Index: 7860112 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0453. Min Act: -0.1700

Data Index: 5368647 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0163. Min Act: -0.1700

Data Index: 1266349 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0158. Min Act: -0.1700

Data Index: 4228971 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0197. Min Act: -0.1700

Data Index: 3350982 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0031. Min Act: -0.1700

Data Index: 8186248 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.9987. Min Act: -0.1700

Data Index: 8646513 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0063. Min Act: -0.1700

Data Index: 3031454 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.9994. Min Act: -0.1700

Data Index: 2340155 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.0899. Min Range: -3.0899

Max Act: 3.0093. Min Act: -0.1700

Data Index: 3928528 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.9832. Min Act: -0.1700

Data Index: 7081471 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.9901. Min Act: -0.1700

Data Index: 7222051 (Open Web Text)

Max Activating Token Index: 2