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

Dataset: Open Web Text

Neuron 1192 in Layer 5

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: 3.9909. Min Range: -3.9909

Max Act: 3.9909. Min Act: -0.1700

Data Index: 3115599 (Open Web Text)

Max Activating Token Index: 222

Text #1

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.9493. Min Act: -0.1700

Data Index: 7547516 (Open Web Text)

Max Activating Token Index: 892

Text #2

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.9292. Min Act: -0.1700

Data Index: 1050554 (Open Web Text)

Max Activating Token Index: 537

Text #3

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.9248. Min Act: -0.1700

Data Index: 1339514 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.9519. Min Act: -0.1700

Data Index: 4480135 (Open Web Text)

Max Activating Token Index: 702

Text #5

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.9124. Min Act: -0.1700

Data Index: 6235881 (Open Web Text)

Max Activating Token Index: 179

Text #6

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.9257. Min Act: -0.1700

Data Index: 8083747 (Open Web Text)

Max Activating Token Index: 957

Text #7

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.9228. Min Act: -0.1700

Data Index: 5591362 (Open Web Text)

Max Activating Token Index: 520

Text #8

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8935. Min Act: -0.1700

Data Index: 6209977 (Open Web Text)

Max Activating Token Index: 849

Text #9

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8806. Min Act: -0.1700

Data Index: 6195437 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.9002. Min Act: -0.1700

Data Index: 1868325 (Open Web Text)

Max Activating Token Index: 639

Text #11

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8946. Min Act: -0.1700

Data Index: 3701547 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8794. Min Act: -0.1700

Data Index: 1411983 (Open Web Text)

Max Activating Token Index: 882

Text #13

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8656. Min Act: -0.1700

Data Index: 5527897 (Open Web Text)

Max Activating Token Index: 1005

Text #14

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8850. Min Act: -0.1700

Data Index: 7928502 (Open Web Text)

Max Activating Token Index: 62

Text #15

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8889. Min Act: -0.1700

Data Index: 7850032 (Open Web Text)

Max Activating Token Index: 1014

Text #16

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8209. Min Act: -0.1700

Data Index: 3812774 (Open Web Text)

Max Activating Token Index: 586

Text #17

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8707. Min Act: -0.1700

Data Index: 1566611 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8335. Min Act: -0.1700

Data Index: 3954944 (Open Web Text)

Max Activating Token Index: 984

Text #19

Max Range: 3.9909. Min Range: -3.9909

Max Act: 3.8467. Min Act: -0.1700

Data Index: 2001669 (Open Web Text)

Max Activating Token Index: 900