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

Dataset: Open Web Text

Neuron 2476 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: 3.2015. Min Range: -3.2015

Max Act: 3.1913. Min Act: -0.1700

Data Index: 7153845 (Open Web Text)

Max Activating Token Index: 946

Text #1

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.2015. Min Act: -0.1700

Data Index: 7518407 (Open Web Text)

Max Activating Token Index: 213

Text #2

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1886. Min Act: -0.1700

Data Index: 992301 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1642. Min Act: -0.1700

Data Index: 764104 (Open Web Text)

Max Activating Token Index: 891

Text #4

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1615. Min Act: -0.1700

Data Index: 8085686 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1599. Min Act: -0.1700

Data Index: 5973520 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1506. Min Act: -0.1700

Data Index: 1554627 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1586. Min Act: -0.1700

Data Index: 2108431 (Open Web Text)

Max Activating Token Index: 172

Text #8

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1496. Min Act: -0.1700

Data Index: 6049022 (Open Web Text)

Max Activating Token Index: 182

Text #9

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1457. Min Act: -0.1700

Data Index: 2511179 (Open Web Text)

Max Activating Token Index: 763

Text #10

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1174. Min Act: -0.1700

Data Index: 5637469 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1094. Min Act: -0.1700

Data Index: 7580671 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0949. Min Act: -0.1700

Data Index: 5411798 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1014. Min Act: -0.1700

Data Index: 4931744 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.1013. Min Act: -0.1700

Data Index: 1672686 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0806. Min Act: -0.1700

Data Index: 431858 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0808. Min Act: -0.1700

Data Index: 5659871 (Open Web Text)

Max Activating Token Index: 208

Text #17

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0811. Min Act: -0.1700

Data Index: 2799905 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0765. Min Act: -0.1700

Data Index: 597820 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0821. Min Act: -0.1700

Data Index: 2933506 (Open Web Text)

Max Activating Token Index: 98