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

Dataset: Open Web Text

Neuron 1518 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: 3.4767. Min Range: -3.4767

Max Act: 3.4767. Min Act: -0.1700

Data Index: 5470469 (Open Web Text)

Max Activating Token Index: 241

Text #1

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.4589. Min Act: -0.1700

Data Index: 2145469 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.4589. Min Act: -0.1700

Data Index: 4506733 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.4589. Min Act: -0.1700

Data Index: 5701366 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3987. Min Act: -0.1700

Data Index: 1621245 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.4033. Min Act: -0.1700

Data Index: 7403023 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.4016. Min Act: -0.1700

Data Index: 3596901 (Open Web Text)

Max Activating Token Index: 560

Text #7

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3752. Min Act: -0.1700

Data Index: 8568682 (Open Web Text)

Max Activating Token Index: 873

Text #8

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3718. Min Act: -0.1700

Data Index: 4518928 (Open Web Text)

Max Activating Token Index: 642

Text #9

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3717. Min Act: -0.1700

Data Index: 3382730 (Open Web Text)

Max Activating Token Index: 283

Text #10

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3393. Min Act: -0.1700

Data Index: 8628939 (Open Web Text)

Max Activating Token Index: 903

Text #11

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3591. Min Act: -0.1700

Data Index: 3490624 (Open Web Text)

Max Activating Token Index: 883

Text #12

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3418. Min Act: -0.1700

Data Index: 1584367 (Open Web Text)

Max Activating Token Index: 562

Text #13

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3096. Min Act: -0.1700

Data Index: 6658943 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3182. Min Act: -0.1700

Data Index: 3943302 (Open Web Text)

Max Activating Token Index: 480

Text #15

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3096. Min Act: -0.1700

Data Index: 5441783 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3109. Min Act: -0.1700

Data Index: 5837893 (Open Web Text)

Max Activating Token Index: 750

Text #17

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3038. Min Act: -0.1700

Data Index: 7631059 (Open Web Text)

Max Activating Token Index: 67

Text #18

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3121. Min Act: -0.1700

Data Index: 7308105 (Open Web Text)

Max Activating Token Index: 931

Text #19

Max Range: 3.4767. Min Range: -3.4767

Max Act: 3.3190. Min Act: -0.1700

Data Index: 7621101 (Open Web Text)

Max Activating Token Index: 795