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

Dataset: Open Web Text

Neuron 270 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: 2.0752. Min Range: -2.0752

Max Act: 2.0752. Min Act: -0.1699

Data Index: 4289755 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 2.0752. Min Range: -2.0752

Max Act: 2.0548. Min Act: -0.1700

Data Index: 2320376 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.0752. Min Range: -2.0752

Max Act: 2.0534. Min Act: -0.1572

Data Index: 7228188 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.0752. Min Range: -2.0752

Max Act: 2.0122. Min Act: -0.1663

Data Index: 4991575 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9852. Min Act: -0.1700

Data Index: 6844159 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9580. Min Act: -0.1700

Data Index: 2057903 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9511. Min Act: -0.1700

Data Index: 6200772 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9497. Min Act: -0.1700

Data Index: 3724982 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9339. Min Act: -0.1691

Data Index: 4991573 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9234. Min Act: -0.1700

Data Index: 2606611 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9352. Min Act: -0.1700

Data Index: 3146137 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9440. Min Act: -0.1700

Data Index: 6696350 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9266. Min Act: -0.1700

Data Index: 2325449 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9193. Min Act: -0.1624

Data Index: 4991571 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9111. Min Act: -0.1700

Data Index: 7228189 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9183. Min Act: -0.1700

Data Index: 7675826 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9235. Min Act: -0.1700

Data Index: 3913594 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9199. Min Act: -0.1700

Data Index: 4376607 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.8991. Min Act: -0.1700

Data Index: 5828909 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9088. Min Act: -0.1700

Data Index: 333637 (Open Web Text)

Max Activating Token Index: 5