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

Dataset: Open Web Text

Neuron 1266 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: 3.3068. Min Range: -3.3068

Max Act: 3.3068. Min Act: -0.1700

Data Index: 4110478 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.3013. Min Act: -0.1700

Data Index: 5476266 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2824. Min Act: -0.1700

Data Index: 410285 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2742. Min Act: -0.1700

Data Index: 7361482 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2727. Min Act: -0.1700

Data Index: 5434288 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2759. Min Act: -0.1700

Data Index: 4618596 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2747. Min Act: -0.1700

Data Index: 5747958 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2576. Min Act: -0.1700

Data Index: 7603481 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2528. Min Act: -0.1700

Data Index: 3587726 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2392. Min Act: -0.1700

Data Index: 2120268 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2370. Min Act: -0.1700

Data Index: 3532071 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2392. Min Act: -0.1700

Data Index: 5890168 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2392. Min Act: -0.1700

Data Index: 514855 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2392. Min Act: -0.1700

Data Index: 2878330 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2398. Min Act: -0.1700

Data Index: 3290606 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2392. Min Act: -0.1700

Data Index: 3709206 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2324. Min Act: -0.1700

Data Index: 5537038 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2272. Min Act: -0.1700

Data Index: 4366167 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2314. Min Act: -0.1700

Data Index: 2384660 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.3068. Min Range: -3.3068

Max Act: 3.2309. Min Act: -0.1700

Data Index: 5741532 (Open Web Text)

Max Activating Token Index: 6