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

Dataset: Open Web Text

Neuron 347 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: 3.5442. Min Range: -3.5442

Max Act: 3.5442. Min Act: -0.1700

Data Index: 6108448 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.5268. Min Act: -0.1700

Data Index: 5046244 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.5097. Min Act: -0.1700

Data Index: 2349547 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4985. Min Act: -0.1700

Data Index: 428644 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4693. Min Act: -0.1700

Data Index: 165483 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4611. Min Act: -0.1700

Data Index: 6281112 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4611. Min Act: -0.1700

Data Index: 8766846 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4673. Min Act: -0.1700

Data Index: 6902321 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4591. Min Act: -0.1700

Data Index: 6692767 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4467. Min Act: -0.1700

Data Index: 3343993 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4347. Min Act: -0.1700

Data Index: 6110721 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4440. Min Act: -0.1700

Data Index: 4258677 (Open Web Text)

Max Activating Token Index: 734

Text #12

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4413. Min Act: -0.1700

Data Index: 8538654 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4381. Min Act: -0.1700

Data Index: 3089209 (Open Web Text)

Max Activating Token Index: 796

Text #14

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4541. Min Act: -0.1700

Data Index: 5481391 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4296. Min Act: -0.1700

Data Index: 7245158 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4281. Min Act: -0.1700

Data Index: 6409144 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4115. Min Act: -0.1700

Data Index: 6233267 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4114. Min Act: -0.1700

Data Index: 295110 (Open Web Text)

Max Activating Token Index: 207

Text #19

Max Range: 3.5442. Min Range: -3.5442

Max Act: 3.4071. Min Act: -0.1700

Data Index: 6377130 (Open Web Text)

Max Activating Token Index: 6