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

Dataset: Open Web Text

Neuron 2986 in Layer 1

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: 2.0550. Min Range: -2.0550

Max Act: 2.0550. Min Act: -0.1700

Data Index: 57975 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.9931. Min Act: -0.1700

Data Index: 3004131 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.9676. Min Act: -0.1700

Data Index: 7428723 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.9448. Min Act: -0.1700

Data Index: 6941334 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.9280. Min Act: -0.1700

Data Index: 5580801 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.9200. Min Act: -0.1700

Data Index: 7931978 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.9111. Min Act: -0.1700

Data Index: 455706 (Open Web Text)

Max Activating Token Index: 76

Text #7

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.9152. Min Act: -0.1700

Data Index: 4310951 (Open Web Text)

Max Activating Token Index: 72

Text #8

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8997. Min Act: -0.1700

Data Index: 7910227 (Open Web Text)

Max Activating Token Index: 237

Text #9

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8908. Min Act: -0.1700

Data Index: 1106362 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8692. Min Act: -0.1700

Data Index: 1179521 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8788. Min Act: -0.1700

Data Index: 2186870 (Open Web Text)

Max Activating Token Index: 530

Text #12

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8723. Min Act: -0.1700

Data Index: 962925 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8719. Min Act: -0.1700

Data Index: 5132363 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8654. Min Act: -0.1700

Data Index: 3463941 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8548. Min Act: -0.1700

Data Index: 4248413 (Open Web Text)

Max Activating Token Index: 546

Text #16

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8463. Min Act: -0.1700

Data Index: 4070696 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8463. Min Act: -0.1700

Data Index: 3195046 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8410. Min Act: -0.1700

Data Index: 4176565 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.0550. Min Range: -2.0550

Max Act: 1.8535. Min Act: -0.1700

Data Index: 72695 (Open Web Text)

Max Activating Token Index: 5