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

Dataset: Open Web Text

Neuron 2870 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: 3.0059. Min Range: -3.0059

Max Act: 3.0059. Min Act: -0.1700

Data Index: 5141396 (Open Web Text)

Max Activating Token Index: 205

Text #1

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9949. Min Act: -0.1700

Data Index: 5616544 (Open Web Text)

Max Activating Token Index: 228

Text #2

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9856. Min Act: -0.1700

Data Index: 2861897 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9893. Min Act: -0.1700

Data Index: 2129252 (Open Web Text)

Max Activating Token Index: 360

Text #4

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9879. Min Act: -0.1700

Data Index: 6196362 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9727. Min Act: -0.1700

Data Index: 441557 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9635. Min Act: -0.1700

Data Index: 1944666 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9688. Min Act: -0.1700

Data Index: 8264063 (Open Web Text)

Max Activating Token Index: 282

Text #8

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9652. Min Act: -0.1700

Data Index: 7608689 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9724. Min Act: -0.1700

Data Index: 2056357 (Open Web Text)

Max Activating Token Index: 137

Text #10

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9490. Min Act: -0.1700

Data Index: 6787735 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9507. Min Act: -0.1700

Data Index: 5482666 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9511. Min Act: -0.1700

Data Index: 3245278 (Open Web Text)

Max Activating Token Index: 87

Text #13

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9612. Min Act: -0.1700

Data Index: 628780 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9526. Min Act: -0.1700

Data Index: 8040363 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9574. Min Act: -0.1700

Data Index: 579545 (Open Web Text)

Max Activating Token Index: 135

Text #16

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9492. Min Act: -0.1700

Data Index: 8358912 (Open Web Text)

Max Activating Token Index: 83

Text #17

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9546. Min Act: -0.1700

Data Index: 808987 (Open Web Text)

Max Activating Token Index: 49

Text #18

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9509. Min Act: -0.1700

Data Index: 4300536 (Open Web Text)

Max Activating Token Index: 90

Text #19

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9448. Min Act: -0.1700

Data Index: 4633625 (Open Web Text)

Max Activating Token Index: 129