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

Dataset: Open Web Text

Neuron 2235 in Layer 2

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: 1.5982. Min Range: -1.5982

Max Act: 1.5982. Min Act: -0.1700

Data Index: 3950403 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5387. Min Act: -0.1700

Data Index: 3048877 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5251. Min Act: -0.1700

Data Index: 6966340 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5280. Min Act: -0.1700

Data Index: 6895496 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5176. Min Act: -0.1700

Data Index: 6758237 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5121. Min Act: -0.1698

Data Index: 3063041 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4972. Min Act: -0.1697

Data Index: 2546625 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5057. Min Act: -0.1700

Data Index: 1403636 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5067. Min Act: -0.1699

Data Index: 4742340 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4832. Min Act: -0.1699

Data Index: 1639875 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4720. Min Act: -0.1700

Data Index: 651565 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4782. Min Act: -0.1700

Data Index: 7986705 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4664. Min Act: -0.1700

Data Index: 5485589 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4628. Min Act: -0.1700

Data Index: 2360221 (Open Web Text)

Max Activating Token Index: 895

Text #14

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4680. Min Act: -0.1699

Data Index: 4742341 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4580. Min Act: -0.1700

Data Index: 2236872 (Open Web Text)

Max Activating Token Index: 610

Text #16

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4513. Min Act: -0.1700

Data Index: 3805035 (Open Web Text)

Max Activating Token Index: 183

Text #17

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4506. Min Act: -0.1700

Data Index: 251311 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4451. Min Act: -0.1700

Data Index: 7089158 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4549. Min Act: -0.1700

Data Index: 3278153 (Open Web Text)

Max Activating Token Index: 14