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

Dataset: Open Web Text

Neuron 487 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: 3.9883. Min Range: -3.9883

Max Act: 3.9883. Min Act: -0.1700

Data Index: 119458 (Open Web Text)

Max Activating Token Index: 681

Text #1

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9787. Min Act: -0.1700

Data Index: 5842055 (Open Web Text)

Max Activating Token Index: 104

Text #2

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9728. Min Act: -0.1700

Data Index: 4942079 (Open Web Text)

Max Activating Token Index: 281

Text #3

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9265. Min Act: -0.1700

Data Index: 1657540 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9447. Min Act: -0.1700

Data Index: 780206 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9355. Min Act: -0.1700

Data Index: 3768863 (Open Web Text)

Max Activating Token Index: 331

Text #6

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9271. Min Act: -0.1700

Data Index: 4287111 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9572. Min Act: -0.1700

Data Index: 1462023 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9382. Min Act: -0.1700

Data Index: 4487746 (Open Web Text)

Max Activating Token Index: 562

Text #9

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9238. Min Act: -0.1700

Data Index: 8117399 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9245. Min Act: -0.1700

Data Index: 8824838 (Open Web Text)

Max Activating Token Index: 276

Text #11

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9222. Min Act: -0.1700

Data Index: 6986314 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8642. Min Act: -0.1700

Data Index: 4898219 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8952. Min Act: -0.1700

Data Index: 860224 (Open Web Text)

Max Activating Token Index: 449

Text #14

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8560. Min Act: -0.1700

Data Index: 5980465 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8605. Min Act: -0.1700

Data Index: 597842 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8548. Min Act: -0.1700

Data Index: 926231 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8600. Min Act: -0.1700

Data Index: 6183864 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8475. Min Act: -0.1700

Data Index: 414473 (Open Web Text)

Max Activating Token Index: 842

Text #19

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8417. Min Act: -0.1700

Data Index: 1139800 (Open Web Text)

Max Activating Token Index: 58