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

Dataset: Open Web Text

Neuron 27 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: 4.7266. Min Range: -4.7266

Max Act: 4.7266. Min Act: -0.1700

Data Index: 3687802 (Open Web Text)

Max Activating Token Index: 30

Text #1

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.5329. Min Act: -0.1700

Data Index: 1882810 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.5565. Min Act: -0.1700

Data Index: 8361274 (Open Web Text)

Max Activating Token Index: 245

Text #3

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4982. Min Act: -0.1700

Data Index: 7670545 (Open Web Text)

Max Activating Token Index: 480

Text #4

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.5062. Min Act: -0.1700

Data Index: 7765024 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4988. Min Act: -0.1700

Data Index: 2453889 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4923. Min Act: -0.1700

Data Index: 6481277 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4612. Min Act: -0.1700

Data Index: 3821712 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4641. Min Act: -0.1700

Data Index: 1495492 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4662. Min Act: -0.1700

Data Index: 862866 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4707. Min Act: -0.1700

Data Index: 3447843 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4852. Min Act: -0.1700

Data Index: 2364936 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4806. Min Act: -0.1700

Data Index: 5687170 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4914. Min Act: -0.1700

Data Index: 1353881 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4832. Min Act: -0.1700

Data Index: 1578286 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4517. Min Act: -0.1700

Data Index: 3271966 (Open Web Text)

Max Activating Token Index: 93

Text #16

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4503. Min Act: -0.1700

Data Index: 3181912 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4342. Min Act: -0.1700

Data Index: 2428306 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4492. Min Act: -0.1700

Data Index: 2501981 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.7266. Min Range: -4.7266

Max Act: 4.4718. Min Act: -0.1700

Data Index: 3595740 (Open Web Text)

Max Activating Token Index: 11