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

Dataset: Open Web Text

Neuron 2731 in Layer 6

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: 5.7524. Min Range: -5.7524

Max Act: 5.7524. Min Act: -0.1700

Data Index: 3168658 (Open Web Text)

Max Activating Token Index: 279

Text #1

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.7208. Min Act: -0.1700

Data Index: 4470821 (Open Web Text)

Max Activating Token Index: 237

Text #2

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.7041. Min Act: -0.1700

Data Index: 3142577 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.6449. Min Act: -0.1700

Data Index: 2690431 (Open Web Text)

Max Activating Token Index: 714

Text #4

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.6002. Min Act: -0.1700

Data Index: 3652973 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.5335. Min Act: -0.1700

Data Index: 5266362 (Open Web Text)

Max Activating Token Index: 830

Text #6

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.5271. Min Act: -0.1700

Data Index: 4082087 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.5245. Min Act: -0.1700

Data Index: 3558879 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.5415. Min Act: -0.1700

Data Index: 6783999 (Open Web Text)

Max Activating Token Index: 157

Text #9

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.5647. Min Act: -0.1700

Data Index: 2866191 (Open Web Text)

Max Activating Token Index: 796

Text #10

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.5008. Min Act: -0.1700

Data Index: 7846019 (Open Web Text)

Max Activating Token Index: 967

Text #11

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.4912. Min Act: -0.1700

Data Index: 3010800 (Open Web Text)

Max Activating Token Index: 669

Text #12

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.4939. Min Act: -0.1700

Data Index: 3680241 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.4672. Min Act: -0.1700

Data Index: 7627857 (Open Web Text)

Max Activating Token Index: 454

Text #14

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.5006. Min Act: -0.1700

Data Index: 5015447 (Open Web Text)

Max Activating Token Index: 698

Text #15

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.4617. Min Act: -0.1700

Data Index: 38175 (Open Web Text)

Max Activating Token Index: 219

Text #16

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.4728. Min Act: -0.1700

Data Index: 4104621 (Open Web Text)

Max Activating Token Index: 957

Text #17

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.4070. Min Act: -0.1700

Data Index: 5908631 (Open Web Text)

Max Activating Token Index: 725

Text #18

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.3611. Min Act: -0.1700

Data Index: 4248869 (Open Web Text)

Max Activating Token Index: 879

Text #19

Max Range: 5.7524. Min Range: -5.7524

Max Act: 5.3958. Min Act: -0.1700

Data Index: 4677819 (Open Web Text)

Max Activating Token Index: 259