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

Dataset: Open Web Text

Neuron 1835 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: 4.0330. Min Range: -4.0330

Max Act: 4.0330. Min Act: -0.1700

Data Index: 3847556 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 4.0330. Min Range: -4.0330

Max Act: 4.0027. Min Act: -0.1700

Data Index: 4248409 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 4.0330. Min Range: -4.0330

Max Act: 4.0224. Min Act: -0.1700

Data Index: 4807842 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.9966. Min Act: -0.1700

Data Index: 5031862 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.9775. Min Act: -0.1700

Data Index: 4844848 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.9470. Min Act: -0.1700

Data Index: 4436577 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.9265. Min Act: -0.1700

Data Index: 4108239 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8775. Min Act: -0.1700

Data Index: 4829624 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8635. Min Act: -0.1700

Data Index: 5795431 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8468. Min Act: -0.1700

Data Index: 2098500 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8486. Min Act: -0.1700

Data Index: 6465954 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8520. Min Act: -0.1700

Data Index: 779649 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8540. Min Act: -0.1700

Data Index: 1133148 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8450. Min Act: -0.1700

Data Index: 4584768 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8395. Min Act: -0.1700

Data Index: 4714537 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8606. Min Act: -0.1700

Data Index: 1718576 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8244. Min Act: -0.1700

Data Index: 1588008 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8291. Min Act: -0.1700

Data Index: 4559979 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8271. Min Act: -0.1700

Data Index: 4764386 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 4.0330. Min Range: -4.0330

Max Act: 3.8248. Min Act: -0.1700

Data Index: 4765397 (Open Web Text)

Max Activating Token Index: 5