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

Dataset: Open Web Text

Neuron 3050 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: 7.1291. Min Range: -7.1291

Max Act: 7.1291. Min Act: -0.1700

Data Index: 380803 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.6726. Min Act: -0.1700

Data Index: 2907236 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.6104. Min Act: -0.1700

Data Index: 6585964 (Open Web Text)

Max Activating Token Index: 918

Text #3

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.4714. Min Act: -0.1700

Data Index: 3200918 (Open Web Text)

Max Activating Token Index: 913

Text #4

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.3880. Min Act: -0.1700

Data Index: 4588814 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.2836. Min Act: -0.1700

Data Index: 6673997 (Open Web Text)

Max Activating Token Index: 48

Text #6

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.2848. Min Act: -0.1700

Data Index: 8592411 (Open Web Text)

Max Activating Token Index: 435

Text #7

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.2549. Min Act: -0.1700

Data Index: 67785 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.2089. Min Act: -0.1700

Data Index: 4898371 (Open Web Text)

Max Activating Token Index: 309

Text #9

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.1779. Min Act: -0.1700

Data Index: 5770777 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.1613. Min Act: -0.1700

Data Index: 6272204 (Open Web Text)

Max Activating Token Index: 184

Text #11

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.1140. Min Act: -0.1700

Data Index: 2910178 (Open Web Text)

Max Activating Token Index: 866

Text #12

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.0929. Min Act: -0.1700

Data Index: 4010180 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.0519. Min Act: -0.1700

Data Index: 2195029 (Open Web Text)

Max Activating Token Index: 138

Text #14

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.1089. Min Act: -0.1700

Data Index: 2026220 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.0409. Min Act: -0.1700

Data Index: 885017 (Open Web Text)

Max Activating Token Index: 30

Text #16

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.0537. Min Act: -0.1700

Data Index: 3179796 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 7.1291. Min Range: -7.1291

Max Act: 6.0002. Min Act: -0.1700

Data Index: 5493236 (Open Web Text)

Max Activating Token Index: 752

Text #18

Max Range: 7.1291. Min Range: -7.1291

Max Act: 5.9709. Min Act: -0.1700

Data Index: 1939602 (Open Web Text)

Max Activating Token Index: 454

Text #19

Max Range: 7.1291. Min Range: -7.1291

Max Act: 5.9859. Min Act: -0.1700

Data Index: 36774 (Open Web Text)

Max Activating Token Index: 247