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

Dataset: Open Web Text

Neuron 630 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: 1.9980. Min Range: -1.9980

Max Act: 1.9980. Min Act: -0.1700

Data Index: 1687055 (Open Web Text)

Max Activating Token Index: 356

Text #1

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8922. Min Act: -0.1700

Data Index: 6654697 (Open Web Text)

Max Activating Token Index: 340

Text #2

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8905. Min Act: -0.1700

Data Index: 5611641 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8648. Min Act: -0.1700

Data Index: 2865495 (Open Web Text)

Max Activating Token Index: 986

Text #4

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8550. Min Act: -0.1700

Data Index: 2715878 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8634. Min Act: -0.1700

Data Index: 1331694 (Open Web Text)

Max Activating Token Index: 426

Text #6

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8484. Min Act: -0.1700

Data Index: 6629896 (Open Web Text)

Max Activating Token Index: 910

Text #7

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8257. Min Act: -0.1700

Data Index: 7199675 (Open Web Text)

Max Activating Token Index: 201

Text #8

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8317. Min Act: -0.1700

Data Index: 8253989 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8217. Min Act: -0.1700

Data Index: 3430763 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8272. Min Act: -0.1700

Data Index: 3479194 (Open Web Text)

Max Activating Token Index: 828

Text #11

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8195. Min Act: -0.1700

Data Index: 4801046 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8152. Min Act: -0.1699

Data Index: 3880326 (Open Web Text)

Max Activating Token Index: 859

Text #13

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8396. Min Act: -0.1699

Data Index: 6298000 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8012. Min Act: -0.1700

Data Index: 4336884 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.7964. Min Act: -0.1700

Data Index: 4614774 (Open Web Text)

Max Activating Token Index: 539

Text #16

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.7873. Min Act: -0.1700

Data Index: 6507430 (Open Web Text)

Max Activating Token Index: 170

Text #17

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.8090. Min Act: -0.1700

Data Index: 3527929 (Open Web Text)

Max Activating Token Index: 208

Text #18

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.7863. Min Act: -0.1700

Data Index: 4641346 (Open Web Text)

Max Activating Token Index: 505

Text #19

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.7994. Min Act: -0.1700

Data Index: 5590961 (Open Web Text)

Max Activating Token Index: 277