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

Dataset: Open Web Text

Neuron 448 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: 4.3384. Min Range: -4.3384

Max Act: 4.3384. Min Act: -0.1700

Data Index: 5258460 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2833. Min Act: -0.1700

Data Index: 5730471 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2809. Min Act: -0.1700

Data Index: 2701474 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2708. Min Act: -0.1700

Data Index: 2124768 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2662. Min Act: -0.1700

Data Index: 4457386 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2547. Min Act: -0.1700

Data Index: 4420978 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2542. Min Act: -0.1700

Data Index: 4208055 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2524. Min Act: -0.1700

Data Index: 8323294 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2647. Min Act: -0.1700

Data Index: 8155616 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2516. Min Act: -0.1700

Data Index: 8145698 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2576. Min Act: -0.1700

Data Index: 7917355 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2697. Min Act: -0.1700

Data Index: 7492053 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2264. Min Act: -0.1700

Data Index: 3651705 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2178. Min Act: -0.1700

Data Index: 3653082 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2217. Min Act: -0.1700

Data Index: 3744427 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2142. Min Act: -0.1700

Data Index: 1613352 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2258. Min Act: -0.1700

Data Index: 3749573 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2219. Min Act: -0.1700

Data Index: 1789957 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2323. Min Act: -0.1700

Data Index: 1800430 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2458. Min Act: -0.1700

Data Index: 4148863 (Open Web Text)

Max Activating Token Index: 6