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

Dataset: Open Web Text

Neuron 2030 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: 3.4068. Min Range: -3.4068

Max Act: 3.4068. Min Act: -0.1700

Data Index: 2234219 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.4033. Min Act: -0.1700

Data Index: 6966677 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3759. Min Act: -0.1700

Data Index: 387865 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3849. Min Act: -0.1700

Data Index: 2021468 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3849. Min Act: -0.1700

Data Index: 2486017 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3849. Min Act: -0.1700

Data Index: 1931898 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3945. Min Act: -0.1700

Data Index: 6847313 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3849. Min Act: -0.1700

Data Index: 1425201 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3849. Min Act: -0.1700

Data Index: 1250534 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3970. Min Act: -0.1700

Data Index: 3410843 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3849. Min Act: -0.1700

Data Index: 6324750 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3751. Min Act: -0.1700

Data Index: 2473638 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3523. Min Act: -0.1700

Data Index: 6400906 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3423. Min Act: -0.1700

Data Index: 8038955 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3239. Min Act: -0.1700

Data Index: 54228 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3516. Min Act: -0.1700

Data Index: 430376 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3343. Min Act: -0.1700

Data Index: 7574450 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3258. Min Act: -0.1700

Data Index: 6233279 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3184. Min Act: -0.1700

Data Index: 7135934 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3100. Min Act: -0.1700

Data Index: 2982627 (Open Web Text)

Max Activating Token Index: 2