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

Dataset: Open Web Text

Neuron 1471 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: 4.8998. Min Range: -4.8998

Max Act: 4.8998. Min Act: -0.1700

Data Index: 1338153 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.8566. Min Act: -0.1700

Data Index: 8635630 (Open Web Text)

Max Activating Token Index: 427

Text #2

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.8314. Min Act: -0.1700

Data Index: 7197346 (Open Web Text)

Max Activating Token Index: 750

Text #3

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.8013. Min Act: -0.1700

Data Index: 6568558 (Open Web Text)

Max Activating Token Index: 377

Text #4

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.7943. Min Act: -0.1700

Data Index: 6809997 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.7815. Min Act: -0.1700

Data Index: 4219021 (Open Web Text)

Max Activating Token Index: 982

Text #6

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6885. Min Act: -0.1700

Data Index: 6764747 (Open Web Text)

Max Activating Token Index: 1000

Text #7

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.7409. Min Act: -0.1700

Data Index: 3869941 (Open Web Text)

Max Activating Token Index: 554

Text #8

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6536. Min Act: -0.1700

Data Index: 5978264 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6450. Min Act: -0.1700

Data Index: 7448167 (Open Web Text)

Max Activating Token Index: 902

Text #10

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6362. Min Act: -0.1700

Data Index: 929719 (Open Web Text)

Max Activating Token Index: 794

Text #11

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6146. Min Act: -0.1700

Data Index: 8199340 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6597. Min Act: -0.1700

Data Index: 5776979 (Open Web Text)

Max Activating Token Index: 440

Text #13

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6525. Min Act: -0.1700

Data Index: 2113273 (Open Web Text)

Max Activating Token Index: 815

Text #14

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6428. Min Act: -0.1700

Data Index: 153047 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6005. Min Act: -0.1700

Data Index: 7729932 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.6253. Min Act: -0.1700

Data Index: 6074698 (Open Web Text)

Max Activating Token Index: 896

Text #17

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.5643. Min Act: -0.1700

Data Index: 3762668 (Open Web Text)

Max Activating Token Index: 702

Text #18

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.5799. Min Act: -0.1700

Data Index: 3538105 (Open Web Text)

Max Activating Token Index: 108

Text #19

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.5722. Min Act: -0.1700

Data Index: 1338136 (Open Web Text)

Max Activating Token Index: 210