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

Dataset: Open Web Text

Neuron 1902 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: 2.8605. Min Range: -2.8605

Max Act: 2.8605. Min Act: -0.1700

Data Index: 4775584 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.8306. Min Act: -0.1700

Data Index: 2489299 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.8214. Min Act: -0.1700

Data Index: 5597018 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.8173. Min Act: -0.1700

Data Index: 3439282 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.8109. Min Act: -0.1700

Data Index: 246013 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.8090. Min Act: -0.1700

Data Index: 3737240 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7909. Min Act: -0.1700

Data Index: 3854517 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7960. Min Act: -0.1700

Data Index: 2971289 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7860. Min Act: -0.1700

Data Index: 7081388 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7841. Min Act: -0.1700

Data Index: 8449946 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7728. Min Act: -0.1700

Data Index: 3361804 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7867. Min Act: -0.1700

Data Index: 3417873 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7880. Min Act: -0.1700

Data Index: 286588 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7803. Min Act: -0.1700

Data Index: 5177831 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7821. Min Act: -0.1700

Data Index: 3792088 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7883. Min Act: -0.1700

Data Index: 1342662 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7787. Min Act: -0.1700

Data Index: 6094408 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7743. Min Act: -0.1700

Data Index: 1139827 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7767. Min Act: -0.1700

Data Index: 3526486 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.8605. Min Range: -2.8605

Max Act: 2.7771. Min Act: -0.1700

Data Index: 2586893 (Open Web Text)

Max Activating Token Index: 4