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

Dataset: Open Web Text

Neuron 1198 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: 3.0017. Min Range: -3.0017

Max Act: 3.0017. Min Act: -0.1700

Data Index: 5168377 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8628. Min Act: -0.1700

Data Index: 545788 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8455. Min Act: -0.1700

Data Index: 7119403 (Open Web Text)

Max Activating Token Index: 815

Text #3

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8414. Min Act: -0.1700

Data Index: 3645689 (Open Web Text)

Max Activating Token Index: 684

Text #4

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8455. Min Act: -0.1700

Data Index: 7200860 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8458. Min Act: -0.1700

Data Index: 4824576 (Open Web Text)

Max Activating Token Index: 814

Text #6

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8335. Min Act: -0.1700

Data Index: 4176038 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8249. Min Act: -0.1700

Data Index: 7367376 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8230. Min Act: -0.1700

Data Index: 3143701 (Open Web Text)

Max Activating Token Index: 804

Text #9

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8373. Min Act: -0.1700

Data Index: 3145830 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8257. Min Act: -0.1700

Data Index: 2738295 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8205. Min Act: -0.1700

Data Index: 6029210 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8162. Min Act: -0.1700

Data Index: 708363 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8130. Min Act: -0.1700

Data Index: 2870459 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8107. Min Act: -0.1700

Data Index: 4213203 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8226. Min Act: -0.1700

Data Index: 2828444 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8061. Min Act: -0.1700

Data Index: 4538683 (Open Web Text)

Max Activating Token Index: 269

Text #17

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8064. Min Act: -0.1700

Data Index: 7873468 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.8081. Min Act: -0.1700

Data Index: 8535263 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.0017. Min Range: -3.0017

Max Act: 2.7991. Min Act: -0.1700

Data Index: 7069685 (Open Web Text)

Max Activating Token Index: 385