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

Dataset: Open Web Text

Neuron 426 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: 4.5314. Min Range: -4.5314

Max Act: 4.5309. Min Act: -0.1700

Data Index: 8714525 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.5314. Min Act: -0.1700

Data Index: 333858 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4837. Min Act: -0.1700

Data Index: 6472171 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4877. Min Act: -0.1700

Data Index: 5083706 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4622. Min Act: -0.1700

Data Index: 6092686 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4644. Min Act: -0.1700

Data Index: 2946466 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4788. Min Act: -0.1700

Data Index: 3139052 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4464. Min Act: -0.1700

Data Index: 8357712 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4698. Min Act: -0.1700

Data Index: 2276179 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4542. Min Act: -0.1700

Data Index: 5986529 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4264. Min Act: -0.1700

Data Index: 6428487 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4192. Min Act: -0.1700

Data Index: 1710275 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4299. Min Act: -0.1700

Data Index: 2552679 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4413. Min Act: -0.1700

Data Index: 4703905 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4409. Min Act: -0.1700

Data Index: 767736 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4121. Min Act: -0.1700

Data Index: 5390334 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.4116. Min Act: -0.1700

Data Index: 5613822 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.3931. Min Act: -0.1700

Data Index: 1604427 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.3991. Min Act: -0.1700

Data Index: 5241358 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.5314. Min Range: -4.5314

Max Act: 4.3861. Min Act: -0.1700

Data Index: 1228448 (Open Web Text)

Max Activating Token Index: 5