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

Dataset: Open Web Text

Neuron 539 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: 3.3616. Min Range: -3.3616

Max Act: 3.3616. Min Act: -0.1700

Data Index: 3322523 (Open Web Text)

Max Activating Token Index: 224

Text #1

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.3521. Min Act: -0.1700

Data Index: 8213222 (Open Web Text)

Max Activating Token Index: 724

Text #2

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.3083. Min Act: -0.1700

Data Index: 7906280 (Open Web Text)

Max Activating Token Index: 358

Text #3

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.3321. Min Act: -0.1700

Data Index: 4977674 (Open Web Text)

Max Activating Token Index: 849

Text #4

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2799. Min Act: -0.1700

Data Index: 7423938 (Open Web Text)

Max Activating Token Index: 782

Text #5

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2633. Min Act: -0.1700

Data Index: 1833165 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2573. Min Act: -0.1700

Data Index: 379404 (Open Web Text)

Max Activating Token Index: 914

Text #7

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2169. Min Act: -0.1700

Data Index: 6292870 (Open Web Text)

Max Activating Token Index: 406

Text #8

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2426. Min Act: -0.1700

Data Index: 3007718 (Open Web Text)

Max Activating Token Index: 927

Text #9

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2255. Min Act: -0.1700

Data Index: 7902440 (Open Web Text)

Max Activating Token Index: 41

Text #10

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2184. Min Act: -0.1700

Data Index: 1604828 (Open Web Text)

Max Activating Token Index: 973

Text #11

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2026. Min Act: -0.1700

Data Index: 3627756 (Open Web Text)

Max Activating Token Index: 115

Text #12

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2227. Min Act: -0.1700

Data Index: 6075030 (Open Web Text)

Max Activating Token Index: 816

Text #13

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1705. Min Act: -0.1700

Data Index: 4251949 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1934. Min Act: -0.1700

Data Index: 219846 (Open Web Text)

Max Activating Token Index: 672

Text #15

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2014. Min Act: -0.1700

Data Index: 6711968 (Open Web Text)

Max Activating Token Index: 433

Text #16

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.2033. Min Act: -0.1700

Data Index: 4178538 (Open Web Text)

Max Activating Token Index: 764

Text #17

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1972. Min Act: -0.1700

Data Index: 2021142 (Open Web Text)

Max Activating Token Index: 687

Text #18

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1816. Min Act: -0.1700

Data Index: 2332686 (Open Web Text)

Max Activating Token Index: 86

Text #19

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.1942. Min Act: -0.1700

Data Index: 7765502 (Open Web Text)

Max Activating Token Index: 58