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

Dataset: Open Web Text

Neuron 2655 in Layer 4

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: 3.0464. Min Range: -3.0464

Max Act: 3.0464. Min Act: -0.1700

Data Index: 8209601 (Open Web Text)

Max Activating Token Index: 189

Text #1

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.9946. Min Act: -0.1700

Data Index: 1506003 (Open Web Text)

Max Activating Token Index: 279

Text #2

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.8897. Min Act: -0.1700

Data Index: 8118513 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.8650. Min Act: -0.1700

Data Index: 6068454 (Open Web Text)

Max Activating Token Index: 850

Text #4

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.8617. Min Act: -0.1700

Data Index: 2213649 (Open Web Text)

Max Activating Token Index: 449

Text #5

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.8478. Min Act: -0.1700

Data Index: 4684744 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.8392. Min Act: -0.1700

Data Index: 1741137 (Open Web Text)

Max Activating Token Index: 926

Text #7

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.8184. Min Act: -0.1700

Data Index: 1823075 (Open Web Text)

Max Activating Token Index: 938

Text #8

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.8187. Min Act: -0.1700

Data Index: 2348366 (Open Web Text)

Max Activating Token Index: 291

Text #9

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7980. Min Act: -0.1700

Data Index: 4405899 (Open Web Text)

Max Activating Token Index: 822

Text #10

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7746. Min Act: -0.1700

Data Index: 3556214 (Open Web Text)

Max Activating Token Index: 258

Text #11

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7711. Min Act: -0.1700

Data Index: 3776366 (Open Web Text)

Max Activating Token Index: 964

Text #12

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7657. Min Act: -0.1700

Data Index: 7482601 (Open Web Text)

Max Activating Token Index: 221

Text #13

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7858. Min Act: -0.1700

Data Index: 5928896 (Open Web Text)

Max Activating Token Index: 977

Text #14

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7810. Min Act: -0.1700

Data Index: 7046319 (Open Web Text)

Max Activating Token Index: 232

Text #15

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7805. Min Act: -0.1700

Data Index: 5385509 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7713. Min Act: -0.1700

Data Index: 6235728 (Open Web Text)

Max Activating Token Index: 666

Text #17

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7416. Min Act: -0.1700

Data Index: 8581320 (Open Web Text)

Max Activating Token Index: 973

Text #18

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7415. Min Act: -0.1700

Data Index: 3937535 (Open Web Text)

Max Activating Token Index: 742

Text #19

Max Range: 3.0464. Min Range: -3.0464

Max Act: 2.7363. Min Act: -0.1700

Data Index: 2631825 (Open Web Text)

Max Activating Token Index: 759